sergiogaiotto / Data-Science-Study-Materials

"Big data is at the foundation of all the megatrends that are happening." – Chris Lynch

Data science is an inter-disciplinary field that uses scientific methods, processes, algorithms and systems to extract knowledge and insights from many structural and unstructured data. Data science is related to data mining, deep learning and big data.

Data science is a "concept to unify statistics, data analysis, machine learning and their related methods" in order to "understand and analyze actual phenomena" with data. It uses techniques and theories drawn from many fields within the context of mathematics, statistics, computer science, and information science. Turing award winner Jim Gray imagined data science as a "fourth paradigm" of science (empirical, theoretical, computational and now data-driven) and asserted that "everything about science is changing because of the impact of information technology" and the data deluge.

Early usage

In 1962, John Tukey described a field he called “data analysis,” which resembles modern data science. Later, attendees at a 1992 statistics symposium at the University of Montpellier II acknowledged the emergence of a new discipline focused on data of various origins and forms, combining established concepts and principles of statistics and data analysis with computing.

The term "data science" has been traced back to 1974, when Peter Naur proposed it as an alternative name for computer science. In 1996, the International Federation of Classification Societies became the first conference to specifically feature data science as a topic. However, the definition was still in flux. In 1997, C.F. Jeff Wu suggested that statistics should be renamed data science. He reasoned that a new name would help statistics shed inaccurate stereotypes, such as being synonymous with accounting, or limited to describing data. In 1998, Chikio Hayashi argued for data science as a new, interdisciplinary concept, with three aspects: data design, collection, and analysis.

During the 1990s, popular terms for the process of finding patterns in datasets (which were increasingly large) included “knowledge discovery” and "data mining."

Modern usage

The modern conception of data science as an independent discipline is sometimes attributed to William S. Cleveland. In a 2001 paper, he advocated an expansion of statistics beyond theory into technical areas; because this would significantly change the field, it warranted a new name. "Data science" became more widely used in the next few years: in 2002, the Committee on Data for Science and Technology launched Data Science Journal. In 2003, Columbia University launched The Journal of Data Science. In 2014, the American Statistical Association's Section on Statistical Learning and Data Mining changed its name to the Section on Statistical Learning and Data Science, reflecting the ascendant popularity of data science.

The professional title of "data scientist" has been attributed to DJ Patil and Jeff Hammerbacher in 2008. Though it was used by the National Science Board in their 2005 report, "Long-Lived Digital Data Collections: Enabling Research and Education in the 21st Century," it referred broadly to any key role in managing a digital data collection.

There is still no consensus on the definition of data science and it is considered by some to be a buzzword.

Careers in data science

Data science is a growing field. A career as a data scientist is ranked at the third best job in America for 2020 by Glassdoor, and was ranked the number one best job from 2016-2019. Data scientists have a median salary of $118,370 per year or $56.91 per hour. Job growth in this field is also above average, with a projected increase of 16% from 2018 to 2028. The largest employer of data scientists in the US is the federal government, employing 28% of the data science workforce. Other large employers of data scientists are computer system design services, research and development laboratories, and colleges and universities. Typically, data scientists work full time, and some work more than 40 hours a week.

Educational path

In order to become a data scientist, there is a significant amount of education and experience required. The first step in becoming a data scientist is to earn a bachelor's degree, typically in a field related to computing or mathematics. Coding bootcamps are also available and can be used as an alternate pre-qualification to supplement a bachelor's degree in another field. Most data scientists also complete a master’s degree or a PhD in data science. Once these qualifications are met, the next step to becoming a data scientist is to apply for an entry-level job in the field. Some data scientists may later choose to specialize in a sub-field of data science.

Specializations and associated careers

• Machine Learning Scientist: Machine learning scientists research new methods of data analysis and create algorithms.
• Data Analyst: Data analysts utilize large data sets to gather information that meets their company’s needs.
• Data Consultant: Data consultants work with businesses to determine the best usage of the information yielded from data analysis.
• Data Architect: Data architects build data solutions that are optimized for performance and design applications.
• Applications Architect: Applications architects track how applications are used throughout a business and how they interact with users and other applications.

Impacts of data science

Big data is very quickly becoming a vital tool for businesses and companies of all sizes. The availability and interpretation of big data has altered the business models of old industries and enabled the creation of new ones. Data-driven businesses are worth $1.2 trillion collectively in 2020, an increase from $333 billion in the year 2015. Data scientists are responsible for breaking down big data into usable information and creating software and algorithms that help companies and organizations determine optimal operations. As big data continues to have a major impact on the world, data science does as well due to the close relationship between the two.

16 Important Data Science Papers:

• Top 10 algorithms in data mining
• MapReduce: Simplified Data Processing on Large Clusters
• The Google File System
• Bigtable: A Distributed Storage System for Structured Data
• The PageRank Citation Ranking: Bringing Order to the Web
• Dynamo: Amazon's Highly Available Key-value Store
• A Few Useful Things to Know about Machine Learning
• Random Forests
• Spanner: Google's Globally Distributed Database
• Pasting Small Votes for Classification in Large Databases and On-Line
• Map-Reduce for Machine Learning on Multicore
• Megastore: Providing Scalable, Highly Available Storage for Interactive Services
• F1: A Distributed SQL Database That Scales
• A Relational Model of Data for Large Shared Data Banks
• Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
• A New Approach to Linear Filtering and Prediction Problems

Machine Learning Formulas:

• 140 Machine Learning Formulas

Best Reference Books - Database Concepts and System:

• A Relational Model of Data for Large Shared Data Banks
• Codd's 12 Rules
• Relational Model for Database Management - Version 2
• An Introduction to Database Systems
• An Introduction to Relational Database Theory
• Database Management Systems Solutions Manual
• Beginning Database Design
• Time and Relational Theory: Temporal Databases in the Relational Model and SQL
• Database System Concepts
• Database Modeling and Design
• Databases types and the relational model: The third manifesto
• Foundations of Databases
• Schaum's Outline of Fundamentals of Relational Databases
• Fundamentals of Relational Database Management Systems
• A First Course in Database Systems
• SQL Clearly Explained
• SQL and Relational Theory
• Architecture of a Database System

Top 9 Data Science Algorithms:

• Apriori algorithm
• Artificial Neural Networks
• Decision Trees
• The k-means clustering algorithm
• Linear Regression
• Logistic Regression
• Principal components analysis
• Recurrent Neural Networks
• Support Vector Machines

Top 11 Data Structure Books:

• Data Structures and Algorithms for Big Databases
• Advanced Data Structures
• The Tomes of Delphi Algorithms and Data Structures
• Compressed Data Structures for Strings: On Searching and Extracting Strings from Compressed Textual Data
• Problem Solving with Data Structures: A Multimedia Approach
• Data Structures and Algorithms for Game Developers
• Data Structures Demystified
• Data Structures & Algorithms
• Fundamentals of Data Structures
• Genetic Programming: Theory and Practice II
• Sams Teach Yourself Data Structures and Algorithms in 24 Hours
• Genetic Algorithms + Data Structures = Evolution Programs

Books and articles about Flowcharts:

• Introduction To Flowcharting
• The Multiple Meanings of a Flowchart
• Understanding Algorithms and flowcharts
• Flowchart
• Flowcharting techniques
• Standard ECMA-4: Flow Charts
• Process Flow Documentation: A Flowchart Guide For Micro & Small Business

Lecture Notes:

• Introduction, linear classification, perceptron update rule (PDF)
• Perceptron convergence, generalization (PDF)
• Maximum margin classification (PDF)
• Classification errors, regularization, logistic regression (PDF)
• Linear regression, estimator bias and variance, active learning (PDF)
• Active learning (cont.), non-linear predictions, kernals (PDF)
• Kernal regression, kernels (PDF)
• Support vector machine (SVM) and kernels, kernel optimization (PDF)
• Model selection (PDF)
• Model selection criteria (PDF)
• Description length, feature selection (PDF)
• Combining classifiers, boosting (PDF)
• Boosting, margin, and complexity (PDF)
• Margin and generalization, mixture models (PDF)
• Mixtures and the expectation maximization (EM) algorithm (PDF)
• EM, regularization, clustering (PDF)
• Clustering (PDF)
• Spectral clustering, Markov models (PDF)
• Hidden Markov models (HMMs) (PDF)
• HMMs (cont.) (PDF)
• Bayesian networks (PDF)
• Learning Bayesian networks (PDF)
• Probabilistic inference - Guest lecture on collaborative filtering (PDF)

Books:

• Hands-On Machine Learning with Scikit-Learn and TensorFlow
• Unstoppable Confidence: How to Use the Power of NLP to Be More Dynamic and Successful
• Python for Finance
• Mining the Social Web
• Deep Learning with Keras
• Agile Data Science
• Practical Statistics for Data Scientists
• Python for Data Analysis
• Python: Deeper Insights into Machine Learning
• Bayesian Reasoning and Machine Learning
• Applied Predictive Modeling
• Machine Learning in Python
• Machine Learning for the Web
• The Elements of Statistical Learning
• Learning TensorFlow: A Guide to Building Deep Learning Systems
• Machine Learning for OpenCV
• Principles of Data Science
• Hands-On Data Science and Python Machine Learning
• R Programming for Data Science
• Machine Learning Algorithms
• Exploratory Data Analysis with R
• Reinforcement Learning: An Introduction
• Information Science and Statistics
• An Introduction to Statistical Learning: with Applications in R
• Machine Learning in Action
• Mastering Machine Learning with scikit-learn
• Building Machine Learning Systems with Python
• The Art of Data Science: A Guide for Anyone Who Works with Data
• Deep Learning with TensorFlow
• Natural Language Processing with Python
• Python Data Science Essentials
• Getting Started with TensorFlow
• R in a Nutshell
• Financial Signal Processing and Machine Learning
• Programming Collective Intelligence
• Financial Risk Forecasting: The Theory and Practice of Forecasting Market Risk, with Implementation in R and Matlab
• Advanced Machine Learning with Python
• Mining of Massive Datasets
• Forecasting: Principles and Practice
• Think Bayes: Bayesian Statistics Made Simple
• Think Stats: Exploratory Data Analysis in Python
• The Elements of Data Analytic Style: A guide for people who want to analyze data
• Think Python: How to Think Like a Computer Scientist
• Improving Processes With Statistical Models
• Interactive Data Visualization: The Age of "Look but don't Touch" is Over
• knitr Graphics Manual
• knitr: A General-Purpose Tool for Dynamic Report Generation in R
• Learning from Solution Paths: An Approach to the Credit Assignment Problem
• Metrics That Matter: Creating custom analytics that quantify user behaviors and drive business practices
• Big data: The next frontier for innovation, competition, and productivity
• Rise of the Machines
• Selecting a Visual Analytics Application
• The Power of R and Visual Analytics
• Tidy Data
• Understanding Machine Learning: From Theory to Algorithms
• Visual Analysis Best Practices: Simple Techniques for Making Every Data Visualization Useful and Beautiful
• Visualizing Complex Data with Embedded Plots
• Which chart or graph is right for you?
• 5 best practices for telling great stories with data and why it will make you a better analyst
• The Field Guide to Data Science
• A Course in Machine Learning
• An Interactive Framework for Data Cleaning
• Analyzing the Analyzers: An Introspective Survey of Data Scientists and Their Work
• Consistency Tradeoffs in Modern Distributed Database System Design
• Introduction to Machine Learning with Python
• Mastering Predictive Analytics with R
• Doing Data Science
• Linear Algebra Review and Reference
• Artificial Intelligence: A Modern Approach
• Encyclopedia of Machine Learning and Data Mining
• Python Machine Learning Blueprints
• Machine Learning
• Statistical Techniques in Business and Economics
• Categorical Data Analysis
• Thoughtful Machine Learning with Python
• Deep Learning: A Practitioner's Approach
• Data Science with Java
• Python Data Science Handbook: Essential Tools for Working with Data
• R Deep Learning Essentials
• Storytelling with Data: A Data Visualization Guide for Business Professionals
• Data Science from Scratch
• Data Science For Dummies
• Practical Python AI Projects
• Fundamentals of Deep Learning
• Pattern Recognition and Machine Learning
• Building Data Science Teams
• naked statistics: Stripping the Dread from the Data
• Data Jujitsu
• Computer Age Statistical Inference: Algorithms, Evidence, and Data Science
• Modeling with Data
• Data Mining and Analysis: Fundamental Concepts and Algorithms
• A Brief Introduction to Machine Learning for Engineers
• Types of Machine Learning Algorithms
• Machine Learning: Basic Concepts
• Deep Learning Tutorial
• Machine Learning Algorithms: A Review
• Machine Learning Tutorial
• Demystifying Machine Learning
• A Brief Introduction to Neural Networks
• Machine Learning Algorithms for Classification
• Machine Learning For Dummies
• Introduction to Probability (LECTURE NOTES)
• The Master Algorithm
• An Introduction to Probability Theory and its Applications
• Foundations of Statistical Natural Language Processing
• A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
• A Polynomial-time Nash Equilibrium Algorithm for Repeated Games
• Algorithms for Reinforcement Learning
• An Analysis of Temporal-Difference Learning with Function Approximation
• Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
• Building Machines that Learn and Think for Themselves: Commentary on Lake, Ullman, Tenenbaum, and Gershman, Behavioral and Brain Sciences, 2017
• Computational Learning Theory
• Curiosity-driven Exploration by Self-supervised Prediction
• Curious model-building control systems
• Deep Learning for Reward Design to Improve Monte Carlo Tree Search in ATARI Games
• Deep Recurrent Q-Learning for Partially Observable MDPs
• DeepMDP: Learning Continuous Latent Space Models for Representation Learning
• DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
• A survey of dimension reduction techniques
• Efficiency and Computational Limitations of Learning Algorithms
• Episodic Curiosity through Reachability
• 10703 Deep Reinforcement Learning and Control
• Friend-or-Foe Q-learning in General-Sum Games
• Gaussian Processes for Machine Learning
• An introduction to information theory and entropy
• Independent Component Analysis: Algorithms and Applications
• Making RL practical
• Markov games as a framework for multi-agent reinforcement learning
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Mastering the Game of Go without Human Knowledge
• Monte-Carlo Tree Search: A New Framework for Game AI
• Near-Optimal Reinforcement Learning in Polynomial Time
• Nonlinear Principal Component Analysis Using Autoassociative Neural Networks
• Non-zero-sum Game Theory, Auctions and Negotiation
• PEGASUS: A policy search method for large MDPs and POMDPs
• Playing Atari with Deep Reinforcement Learning
• Policy Gradient Methods for Reinforcement Learning with Function Approximation
• Prefrontal cortex as a meta-reinforcement learning system
• Probability for Statistics and Machine Learning
• Proximal Policy Optimization Algorithms
• Regularization Paths for Generalized Linear Models via Coordinate Descent
• Reinforcement Learning: A Tutorial Survey and Recent Advances
• Reinforcement Learning: An Introduction
• Reinforcement Learning: A Survey
• Reinforcement Learning
• Reinforcement Learning for Long-Run Average Cost
• Solving Stochastic Games
• Statistical Modeling: The Two Cultures
• Introduction to Game Theory: Stochastic Games
• Survey on Independent Component Analysis
• Toward an AI Physicist for Unsupervised Learning
• Xception: Deep Learning with Depthwise Separable Convolutions
• Games with Hidden Information
• Dynamic Routing Between Capsules
• Efficient BackProp
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• End-To-End Memory Networks
• Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition
• Exploring galaxy evolution with generative models
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• FixingWeight Decay Regularization in Adam
• FractalNet: Ultra-Deep Neural Networks without Residuals
• Generative Adversarial Nets
• Geometric deep learning: going beyond Euclidean data
• Going deeper with convolutions
• Gradient-Based Learning Applied to Document Recognition
• Deep Residual Learning for Image Recognition
• "Neural" Computation of Decisions in Optimization Problems
• How transferable are features in deep neural networks?
• ImageNet Classification with Deep Convolutional Neural Networks
• Learning long-term dependencies with gradient descent is difficult
• Learning to Predict the Cosmological Structure Formation
• Long short-term memory
• Mastering the game of Go with deep neural networks and tree search
• Mathematics of Deep Learning
• Maxout Networks
• Mixed precision training
• MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks
• Network In Network
• Neural Architecture Search with Reinforcement Learning
• Neural Arithmetic Logic Units
• Neural Machine Translation by Jointly Learning to Align and Translate
• Neural Networks for Optimal Approximation of Smooth and Analytic Functions
• Neural Ordinary Differential Equations
• Neuro-Dynamic Programming: An Overview
• Number detectors spontaneously emerge in a deep neural network designed for visual object recognition
• On the difficulty of training recurrent neural networks
• Piecewise Linear Multilayer Perceptrons and Dropout
• Practical Recommendations for Gradient-Based Training of Deep Architectures
• QuCumber: wavefunction reconstruction with neural networks
• Rectified Linear Units Improve Restricted Boltzmann Machines
• Representation Learning: A Review and New Perspectives
• Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
• SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
• Session-based Recommendations with Recurrent Neural Networks
• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• SGDR: Stochastic Gradient Descent with Warm Restarts
• Tackling Climate Change with Machine Learning
• The Matrix Calculus You Need For Deep Learning
• Python Data Science Handbook: Essential Tools for Working with Data
• R Deep Learning Essentials
• Storytelling with Data: A Data Visualization Guide for Business Professionals
• Data Science from Scratch
• Data Science For Dummies
• Practical Python AI Projects
• Fundamentals of Deep Learning
• Pattern Recognition and Machine Learning
• Building Data Science Teams
• naked statistics: Stripping the Dread from the Data
• Data Jujitsu
• Computer Age Statistical Inference: Algorithms, Evidence, and Data Science
• Modeling with Data
• Data Mining and Analysis: Fundamental Concepts and Algorithms
• A Brief Introduction to Machine Learning for Engineers
• Types of Machine Learning Algorithms
• Machine Learning: Basic Concepts
• Deep Learning Tutorial
• Machine Learning Algorithms: A Review
• Machine Learning Tutorial
• Demystifying Machine Learning
• A Brief Introduction to Neural Networks
• Machine Learning Algorithms for Classification
• Machine Learning For Dummies
• Introduction to Probability (LECTURE NOTES)
• The Master Algorithm
• An Introduction to Probability Theory and its Applications
• Foundations of Statistical Natural Language Processing
• A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
• A Polynomial-time Nash Equilibrium Algorithm for Repeated Games
• Algorithms for Reinforcement Learning
• An Analysis of Temporal-Difference Learning with Function Approximation
• Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
• Building Machines that Learn and Think for Themselves: Commentary on Lake, Ullman, Tenenbaum, and Gershman, Behavioral and Brain Sciences, 2017
• Computational Learning Theory
• Curiosity-driven Exploration by Self-supervised Prediction
• Curious model-building control systems
• Deep Learning for Reward Design to Improve Monte Carlo Tree Search in ATARI Games
• Deep Recurrent Q-Learning for Partially Observable MDPs
• DeepMDP: Learning Continuous Latent Space Models for Representation Learning
• DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
• A survey of dimension reduction techniques
• Efficiency and Computational Limitations of Learning Algorithms
• Episodic Curiosity through Reachability
• 10703 Deep Reinforcement Learning and Control
• Friend-or-Foe Q-learning in General-Sum Games
• Gaussian Processes for Machine Learning
• An introduction to information theory and entropy
• Independent Component Analysis: Algorithms and Applications
• Making RL practical
• Markov games as a framework for multi-agent reinforcement learning
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Mastering the Game of Go without Human Knowledge
• Monte-Carlo Tree Search: A New Framework for Game AI
• Near-Optimal Reinforcement Learning in Polynomial Time
• Nonlinear Principal Component Analysis Using Autoassociative Neural Networks
• Non-zero-sum Game Theory, Auctions and Negotiation
• PEGASUS: A policy search method for large MDPs and POMDPs
• Playing Atari with Deep Reinforcement Learning
• Policy Gradient Methods for Reinforcement Learning with Function Approximation
• Prefrontal cortex as a meta-reinforcement learning system
• Probability for Statistics and Machine Learning
• Proximal Policy Optimization Algorithms
• Regularization Paths for Generalized Linear Models via Coordinate Descent
• Reinforcement Learning: A Tutorial Survey and Recent Advances
• Reinforcement Learning: An Introduction
• Reinforcement Learning: A Survey
• Reinforcement Learning
• Reinforcement Learning for Long-Run Average Cost
• Solving Stochastic Games
• Statistical Modeling: The Two Cultures
• Introduction to Game Theory: Stochastic Games
• Survey on Independent Component Analysis
• Toward an AI Physicist for Unsupervised Learning
• Xception: Deep Learning with Depthwise Separable Convolutions
• Games with Hidden Information
• Dynamic Routing Between Capsules
• Efficient BackProp
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• End-To-End Memory Networks
• Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition
• Exploring galaxy evolution with generative models
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• FixingWeight Decay Regularization in Adam
• FractalNet: Ultra-Deep Neural Networks without Residuals
• Generative Adversarial Nets
• Geometric deep learning: going beyond Euclidean data
• Going deeper with convolutions
• Gradient-Based Learning Applied to Document Recognition
• Deep Residual Learning for Image Recognition
• "Neural" Computation of Decisions in Optimization Problems
• How transferable are features in deep neural networks?
• ImageNet Classification with Deep Convolutional Neural Networks
• Learning long-term dependencies with gradient descent is difficult
• Learning to Predict the Cosmological Structure Formation
• Long short-term memory
• Mastering the game of Go with deep neural networks and tree search
• Mathematics of Deep Learning
• Maxout Networks
• Mixed precision training
• MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks
• Network In Network
• Neural Architecture Search with Reinforcement Learning
• Neural Arithmetic Logic Units
• Neural Machine Translation by Jointly Learning to Align and Translate
• Neural Networks for Optimal Approximation of Smooth and Analytic Functions
• Neural Ordinary Differential Equations
• Neuro-Dynamic Programming: An Overview
• Number detectors spontaneously emerge in a deep neural network designed for visual object recognition
• On the difficulty of training Recurrent Neural Networks
• Piecewise Linear Multilayer Perceptrons and Dropout
• Practical Recommendations for Gradient-Based Training of Deep Architectures
• QuCumber: wavefunction reconstruction with neural networks
• Rectified Linear Units Improve Restricted Boltzmann Machines
• Representation Learning: A Review and New Perspectives
• Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
• SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
• Session-based Recommendations with Recurrent Neural Networks
• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• SGDR: Stochastic Gradient Descent with Warm Restarts
• Tackling Climate Change with Machine Learning
• The Matrix Calculus You Need For Deep Learning
• The power of deeper networks for expressing natural functions
• TossingBot: Learning to Throw Arbitrary Objects with Residual Physics
• Uncovering and Mitigating Algorithmic Bias through Learned Latent Structure
• Understanding Convolutional Neural Networks with A Mathematical Model
• Understanding deep learning requires rethinking generalization
• Understanding the difficulty of training deep feedforward neural networks
• Universal Approximation Bounds for Superpositions of a Sigmoidal Function
• Universal Approximation using Radial-Basis-Function Networks
• Unsupervised learning by competing hidden units
• Unsupervised word embeddings capture latent knowledge from materials science literature
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Visualizing and Understanding Recurrent Networks
• Why does deep and cheap learning work so well?
• You Only Look Once: Unified, Real-Time Object Detection
• A Closer Look at Memorization in Deep Networks
• A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay
• A fast learning algorithm for deep belief nets
• A Neural Probabilistic Language Model
• Regularized Evolution for Image Classifier Architecture Search
• An exact mapping between the Variational Renormalization Group and Deep Learning
• Automatic Differentiation in Machine Learning: a Survey
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
• Dive into Deep Learning
• Deep Boltzmann Machines
• Deep Sparse Rectifier Neural Networks
• Deep, Skinny Neural Networks are not Universal Approximators
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
• Discovering physical concepts with neural networks
• Do Neural Networks Show Gestalt Phenomena? An Exploration of the Law of Closure
• Don't Decay the Learning Rate, Increase the Batch Size
• Dropout: A Simple Way to Prevent Neural Networks from Overfitting
• Eyeriss v2: A Flexible and High-Performance Accelerator for Emerging Deep Neural Networks
• Faster Neural Network Training with Data Echoing
• Recent progress in analog memory-based accelerators for deep learning
• Rethinking floating point for deep learning
• An Analysis of Deep Neural Network Models for Practical Applications
• Benchmarking TPU, GPU, and CPU Platforms for Deep Learning
• Fair is Better than Sensational: Man is to Doctor asWoman is to Doctor
• The Measure and Mismeasure of Fairness: A Critical Review of Fair Machine Learning
• For valid generalization, the size of the weights is more important than the size of the network
• Interpretable Machine Learning
• Multi-Agent Reinforcement Learning: a critical survey
• Machine learning at the energy and intensity frontiers of particle physics
• Please Stop Explaining Black Box Models for High-Stakes Decisions
• Regression Error Characteristic Curves
• Restructuring Sparse High Dimensional Data for Effective Retrieval
• Support-Vector Networks
• The Optimality of Naive Bayes
• The Riemannian Geometry of Deep Generative Models
• Theoretical Impediments to Machine Learning
• TherML: Thermodynamics of Machine Learning
• Top 10 algorithms in data mining
• CS260: Machine Learning Theory, Lecture 13: Weak vs. Strong Learning and the Adaboost Algorithm
• A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting
• A Few Useful Things to Know about Machine Learning
• A Survey of Collaborative Filtering Techniques
• A survey of cross-validation procedures for model selection
• Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent
• AdaBoost
• An Efficient Approach for Assessing Hyperparameter Importance
• An Impossibility Theorem for Clustering
• An Interactive Machine Learning Framework
• Boosting the margin: A new explanation for the effectiveness of voting methods
• Data Science: Theories, Models, Algorithms, and Analytics
• The Data Science Design Manual
• Data Mining: Concepts and Techniques
• Data Mining: Practical Machine Learning Tools and Techniques
• Ensemble Methods in Data Mining: Improving Accuracy Through Combining Predictions
• Evaluating Learning Algorithms: A Classification Perspective
• Machine Learning for Hackers
• Real-World Machine Learning
• Machine Learning: An Algorithmic Perspective
• Data Mining Algorithms: Explained Using R
• Large Scale Machine Learning with Python
• Learning to Rank for Information Retrieval and Natural Language Processing
• An Introduction to Pattern Recognition: A MATLAB Approach
• Data Mining and Machine Learning in Cybersecurity
• Machine Learning Refined
• Machine Learning for Health Informatics
• Cluster Analysis: Basic Concepts and Algorithms
• Clustering — Unsupervised Learning
• Supervised and Unsupervised Learning
• Rules of Machine Learning: Best Practices for ML Engineering
• BRIEF NOTES ON STATISTICS: Introduction – why, what and how?
• Brief notes on statistics: Practical aspects of using statistics in research
• Brief notes on statistics: Part 1 - Histograms, averages, measures of spread, probability and the normal distribution
• Brief notes on statistics: Part 2 - Scatter diagrams, correlation (Kendall's and Pearson's) and regression
• Brief notes on statistics: Part 3 - Null hypothesis significance tests and confidence intervals
• Brief notes on statistics: Part 4 - More on regression: multiple regression, p values, confidence intervals, etc

22 Algorithms Books Every Programmer Should Read:

• Computer Algorithms
• The Algorithm Design Manual
• Algorithms: Robert Sedgewick
• Introduction To Algorithms: A Creative Approach
• Elementary Algorithms
• Algorithm Design
• Introduction to Algorithms
• Algorithms: S. Dasgupta
• Mathematics for Computer Science
• Algorithms and Data Structures
• Essential Algorithms: A Practical Approach to Computer Algorithms
• Algorithms in a Nutshell
• grokking algorithms
• Hacker's Delight
• Algorithms to Live By
• Design and Analysis of Algorithms
• Principles of Algorithmic Problem Solving
• Problems on Algorithms
• How to Think About Algorithms
• Programming Challenges: The Programming Contest Training Manual
• Automate This: How Algorithms Took Over Our Markets, Our Jobs, and the World
• The Art of Computer Programming: Volume 1: Fundamental Algorithms

Assignments:

• Problem set 1 with solution
• Problem set 2 with solution
• Problem set 3 with solution
• Problem set 4 with solution
• Problem set 5 with solution

Bayes' Theorem – The Forecasting Pillar of Data Science:

• Bayes' Theorem
• Bayes' Theorem in the 21st Century
• Bayesian Modelling
• Bayesian Reasoning and Machine Learning

Essential Math for Data Science:

• A Beginner's Guide to the Mathematics of Neural Networks
• Advanced Engineering Mathematics
• An Introduction to Statistical Learning with Applications in R
• Bayesian Statistics
• Probability and Statistics Cookbook
• Discovering Statistics Using R
• The Elements of Statistical Learning
• Matrix Computations
• A Probabilistic Theory of Pattern Recognition
• Probability Cheatsheet
• From Algorithms to Z-Scores: Probabilistic and Statistical Modeling in Computer Science
• Think Stats: Probability and Statistics for Programmers
• Introduction to Applied Linear Algebra

Data Science Case Studies:

• Big Data and Data Science: Case Studies
• Big Data Case Study Collection: 7 Amazing Companies That Really Get Big Data
• Data Science Applications and Use Cases
• Towards Simulation-Data Science – a Case Study on Material Failures
• Top Five High-Impact Use Cases for Big Data Analytics
• The Importance of Big Data Analytics in Business: A Case Study
• Big Data Analytics for Smart Manufacturing: Case Studies in Semiconductor Manufacturing
• Decision Support with Big Data: A Case Study in the Hospitality Industry
• Insight and Action Analytics: Three Case Studies to Consider
• Fundamentals of Machine Learning for Predictive Data Analytics: Algorithms, Worked Examples, and Case Studies
• A Systematic Approach for Business Data Analytics with a Real Case Study
• Conceptualizing Big Data: Analysis of Case Studies
• Predictive Analytics: Case Studies in Life and Annuities
• Case study: the implementation of a data-driven industrial analytics methodology and platform for smart manufacturing
• Creating A Minor In Applied Data Science
• Predictive Analytics: A Case Study in Machine-Learning and Claims Databases
• Data Mining Case Studies
• R and Data Mining: Examples and Case Studies

Data Science Tutorials for Beginners:

• A Tutorial on Machine Learning and Data Science Tools with Python
• Data Science Tutorial
• Big Data Analytics Tutorial
• Machine Learning Tutorial
• Deep Learning Tutorial
• Data Mining Tutorial
• The Field Guide to Data Science
• Agile Data Science Tutorial
• Beginner's Guide to Data Science
• Tutorial on Natural Language Processing
• Natural Language Processing: A Tutorial
• Artificial Neural Networks Tutorial
• Machine Learning in Computer Vision
• The Fundamentals of Machine Vision

Lecture Notes by Andrew Ng:

• 01 and 02: Introduction, Regression Analysis and Gradient Descent
• 03: Linear Algebra - review
• 04: Linear Regression with Multiple Variables
• 05: Octave
• 06: Logistic Regression
• 07: Regularization
• 08: Neural Networks - Representation
• 09: Neural Networks - Learning
• 10: Advice for applying machine learning techniques
• 11: Machine Learning System Design
• 12: Support Vector Machines
• 13: Clustering
• 14: Dimensionality Reduction
• 15: Anomaly Detection
• 16: Recommender Systems
• 17: Large Scale Machine Learning
• 18: Application Example - Photo OCR
• Understanding Andrew Ng's Machine Learning Course – Notes and codes

50 selected papers in Data Mining and Machine Learning:

General

Data Mining and Statistics: What’s the Connection?

Data Mining: Statistics and More?, D. Hand, American Statistician, 52(2):112-118.

Data Mining, G. Weiss and B. Davison, in Handbook of Technology Management, John Wiley and Sons, expected 2010.

From Data Mining to Knowledge Discovery in Databases, U. Fayyad, G. Piatesky-Shapiro & P. Smyth, AI Magazine, 17(3):37-54, Fall 1996.

Mining Business Databases, Communications of the ACM, 39(11): 42-48.

10 Challenging Problems in Data Mining Research, Q. Yiang and X. Wu, International Journal of Information Technology & Decision Making, Vol. 5, No. 4, 2006, 597-604.

General Data Mining Methods and Algorithms

Top 10 Algorithms in Data Mining, X. Wu, V. Kumar, J.R. Quinlan, J. Ghosh, Q. Yang, H. motoda, G.J. MClachlan, A. Ng, B. Liu, P.S. Yu, Z. Zhou, M. Steinbach, D. J. Hand, D. Steinberg, Knowl Inf Syst (2008) 141-37.

Induction of Decision Trees, R. Quinlan, Machine Learning, 1(1):81-106, 1986.

Web and Link Mining

The Pagerank Citation Ranking: Bringing Order to the Web, L. Page, S. Brin, R. Motwani, T. Winograd, Technical Report, Stanford University, 1999.

The Structure and Function of Complex Networks, M. E. J. Newman, SIAM Review, 2003, 45, 167-256.

Link Mining: A New Data Mining Challenge, L. Getoor, SIGKDD Explorations, 2003, 5(1), 84-89.

Link Mining: A Survey, L. Getoor, SIGKDD Explorations, 2005, 7(2), 3-12.

Semi-supervised Learning

Semi-Supervised Learning Literature Survey, X. Zhu, Computer Sciences TR 1530, University of Wisconsin — Madison.

Learning with Labeled and Unlabeled Data, M. Seeger, University of Edinburgh (unpublished), 2002.

Person Identification in Webcam Images: An Application of Semi-Supervised Learning, M. Balcan, A. Blum, P. Choi, J. lafferty, B. Pantano, M. Rwebangira, X. Zhu, Proceedings of the 22nd ICML Workshop on Learning with Partially Classified Training Data, 2005.

Learning from Labeled and Unlabeled Data: An Empirical Study across Techniques and Domains, N. Chawla, G. Karakoulas, Journal of Artificial Intelligence Research, 23:331-366, 2005.

Text Classification from Labeled and Unlabeled Documents using EM, K. Nigam, A. McCallum, S. Thrun, T. Mitchell, Machine Learning, 39, 103-134, 2000.

Self-taught Learning: Transfer Learning from Unlabeled Data, R. Raina, A. Battle, H. Lee, B. Packer, A. Ng, in Proceedings of the 24th International Conference on Machine Learning, 2007.

An iterative algorithm for extending learners to a semisupervised setting, M. Culp, G. Michailidis, 2007 Joint Statistical Meetings (JSM), 2007

Get Another Label? Improving Data Quality and Data Mining Using Multiple, Noisy Labelers, V. Sheng, F. Provost, P. Ipeirotis, in Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2008.

Logistic Regression for Partial Labels, in 9th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems, Volume III, pp. 1935-1941, 2002.

Classification with Partial labels, N. Nguyen, R. Caruana, in Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2008.

Induction of Decision Trees from Partially Classified Data Using Belief Functions, M. Bjanger, Norweigen University of Science and Technology, 2000.

Knowledge Discovery in Large Image Databases: Dealing with Uncertainties in Ground Truth, P. Smyth, M. Burl, U. Fayyad, P. Perona, KDD Workshop 1994, AAAI Technical Report WS-94-03, pp. 109-120, 1994.

Active Learning

Improving Generalization with Active Learning, D Cohn, L. Atlas, and R. Ladner, Machine Learning 15(2), 201-221, May 1994.

On Active Learning for Data Acquisition, Z. Zheng and B. Padmanabhan, In Proc. of IEEE Intl. Conf. on Data Mining, 2002.

Active Sampling for Class Probability Estimation and Ranking, M. Saar-Tsechansky and F. Provost, Machine Learning 54:2 2004, 153-178.

The Learning-Curve Sampling Method Applied to Model-Based Clustering, C. Meek, B. Thiesson, and D. Heckerman, Journal of Machine Learning Research 2:397-418, 2002.

Active Sampling for Feature Selection, S. Veeramachaneni and P. Avesani, Third IEEE Conference on Data Mining, 2003.

Heterogeneous Uncertainty Sampling for Supervised Learning, D. Lewis and J. Catlett, In Proceedings of the 11th International Conference on Machine Learning, 148-156, 1994.

Learning When Training Data are Costly: The Effect of Class Distribution on Tree Induction, G. Weiss and F. Provost, Journal of Artificial Intelligence Research, 19:315-354, 2003.

Active Learning using Adaptive Resampling, KDD 2000, 91-98.

Cost-Sensitive Learning

Types of Cost in Inductive Concept Learning, P. Turney, In Proceedings Workshop on Cost-Sensitive Learning at the Seventeenth International Conference on Machine Learning.

Toward Scalable Learning with Non-Uniform Class and Cost Distributions: A Case Study in Credit Card Fraud Detection, P. Chan and S. Stolfo, KDD 1998.

Papers

Learning when Data Sets are Imbalanced and When Costs are Unequal and Unknown, M. Maloof, in ICML Workshop on Learning from Imbalanced Datasets II, 2003.

Uncertainty Sampling Methods for One-class Classifiers, P. Juszcak and R. Duin, in ICML Workshop on Learning from Imbalanced Datasets II, 2003.

C4.5, Class Imbalance, and Cost Sensitivity: Why Under-Sampling beats Over-Sampling, C. Drummond and R. Holte, in ICML Workshop onLearning from Imbalanced Datasets II, 2003.

C4.5 and Imbalanced Data sets: Investigating the effect of sampling method, probabilistic estimate, and decision tree structure, N. Chawla, in ICML Workshop on Learning from Imbalanced Datasets II, 2003.

Wrapper-based Computation and Evaluation of Sampling Methods for Imbalanced Datasets, N. Chawla, L. Hall, and A. Joshi, in Proceedings of the 1st International Workshop on Utility-based Data Mining, 24-33, 2005.

Learning from Little: Comparison of Classifiers Given Little of Classifiers given Little Training, G. Forman and I. Cohen, in 8th European Conference on Principles and Practice of Knowledge Discovery in Databases, 161-172, 2004.

A Multiple Resampling Method for Learning from Imbalanced Data Sets, A. Estabrooks, T. Jo, and N. Japkowicz, in Computational Intelligence, 20(1), 2004.

A Study of the Behavior of Several Methods for Balancing Machine Learning Training Data, G. Batista, R. Prati, and M. Monard, SIGKDD Explorations, 6(1):20-29, 2004.

Class Imbalance versus Small Disjuncts, T. Jo and N. Japkowicz, SIGKDD Explorations, 6(1): 40-49, 2004.

Extreme Re-balancing for SVMs: a Case Study, B. Raskutti and A. Kowalczyk, SIGKDD Explorations, 6(1):60-69, 2004.

Generative Oversampling for Mining Imbalanced Datasets, A. Liu, J. Ghosh, and C. Martin, Third International Conference on Data Mining (DMIN-07), 66-72.

Computing Machinery and Intelligence

Class Imbalances: Are we Focusing on the Right Issue?, N. Japkowicz, in ICML Workshop on Learning from Imbalanced Datasets II, 2003.

Recommender Systems

Trust No One: Evaluating Trust-based Filtering for Recommenders, J. O’Donovan and B. Smyth, In Proceedings of the 19th International Joint Conference on Artificial Intelligence (IJCAI-05), 2005, 1663-1665.

Trust in Recommender Systems, J. O’Donovan and B. Symyth, In Proceedings of the 10th International Conference on Intelligent User Interfaces (IUI-05), 2005, 167-174.

10 Cutting Edge Research-Papers In Computer Vision and Image Generation:

• Spherical CNNs
• Adversarial Examples that Fool both Computer Vision and Time-Limited Humans
• Group Normalization
• A Closed-form Solution to Photorealistic Image Stylization
• Taskonomy: Disentangling Task Transfer Learning
• GANimation: Anatomically-aware Facial Animation from a Single Image
• Self-Attention Generative Adversarial Networks
• Video-to-Video Synthesis
• Everybody Dance Now
• Large Scale GAN Training for High Fidelity Natural Image Synthesis

21 hottest research papers on Computer Vision and Machine Learning:

• HD-CNN: Hierarchical Deep Convolutional Neural Network for Large Scale Visual Recognition
• Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture
• High-for-Low and Low-for-High: Efficient Boundary Detection from Deep Object Features and its Applications to High-Level Vision
• Dense Optical Flow Prediction from a Static Image
• Ask Your Neurons: A Neural-based Approach to Answering Questions about Images
• Learning to See by Moving
• Unsupervised Visual Representation Learning by Context Prediction
• PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization
• Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books
• Deep Networks for Image Super-Resolution with Sparse Prior
• A Deep Visual Correspondence Embedding Model for Stereo Matching Costs
• Conditional Random Fields as Recurrent Neural Networks
• Local Convolutional Features with Unsupervised Training for Image Retrieval
• FlowNet: Learning Optical Flow with Convolutional Networks
• Active Object Localization with Deep Reinforcement Learning
• Deep Neural Decision Forests
• Im2Calories: towards an automated mobile vision food diary
• DeepBox: Learning Objectness with Convolutional Networks
• Flowing ConvNets for Human Pose Estimation in Videos
• Understanding deep features with computer-generated imagery
• Visual Tracking with Fully Convolutional Networks

10 Important AI Research Papers:

• A Computational Approach to Edge Detection
• A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence
• A Threshold Selection Method from Gray-Level Histograms
• Deep Residual Learning for Image Recognition
• Distinctive Image Features from Scale-Invariant Keypoints
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Large-scale Video Classification with Convolutional Neural Networks
• Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference
• Dropout: A Simple Way to Prevent Neural Networks from Overfitting
• Induction of Decision Trees

6 Top NLP Papers:

• Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems
• Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts
• Bridging the Gap between Training and Inference for Neural Machine Translation
• Zero-shotWord Sense Disambiguation using Sense Definition Embeddings
• We need to talk about standard splits
• A Simple Theoretical Model of Importance for Summarization

The 18 Best Books About AI:

• Affective Computing: Focus on Emotion Expression, Synthesis and Recognition
• Common LISP: A Gentle Introduction to Symbolic Computation
• Planning Algorithms
• Artificial Intelligence: Foundations of Computational Agents
• A Course in Machine Learning
• Clever Algorithms: Nature-Inspired Programming Recipes
• Deep Learning with R
• Essentials of Metaheuristics
• From Bricks to Brains: The Embodied Cognitive Science of LEGO Robots
• Logic For Computer Science: Foundations of Automatic Theorem Proving
• Life 3.0: Being Human in the Age of Artificial Intelligence
• Our Final Invention: Artificial Intelligence and the End of the Human Era
• Artificial Intelligence: A Modern Approach
• Python Machine Learning
• The Quest for Artificial Intelligence: A History of Ideas and Achievements
• Simply Logical: Intelligent Reasoning by Example
• Superintelligence
• Virtual Reality for Human Computer Interaction

Top 30 most influential papers in the world of big data:

• Dremel: Interactive Analysis of WebScale Datasets
• Large-scale Incremental Processing Using Distributed Transactions and Notifications
• Availability in Globally Distributed Storage Systems
• Scientific Data Management in the Coming Decade
• What Next? A Dozen Information-Technology Research Goals
• Volley: Automated Data Placement for Geo-Distributed Cloud Services
• Dynamo: Amazon's Highly Available Key-value Store
• Bigtable: A Distributed Storage System for Structured Data
• The Collective: A Cache-Based System Management Architecture
• Cloud Storage for Cloud Computing
• Data-Intensive Supercomputing: The case for DISC
• MapReduce Online
• Frustratingly Easy Domain Adaptation
• The Google File System
• Cassandra - A Decentralized Structured Storage System
• MapReduce: Simplified Data Processing on Large Clusters
• NoSQL Databases
• Chord: A Scalable Peer-to-peer Lookup Protocol for Internet Applications
• Parallax: Virtual Disks for Virtual Machines
• Pastry: Scalable, decentralized object location and routing for large-scale peer-to-peer systems
• Large-scale Incremental Processing Using Distributed Transactions and Notifications
• Interpreting the Data: Parallel Analysis with Sawzall
• Spanner: Google's Globally-Distributed Database
• RCFile: A Fast and Space-efficient Data Placement Structure in MapReduce-based Warehouse Systems
• What is Data Science?
• The Dangers of Replication and a Solution
• Data clustering: 50 years beyond K-means
• Q-Clouds: Managing Performance Interference Effects for QoS-Aware Clouds
• Lithium: Virtual Machine Storage for the Cloud
• Bayesian Semi-supervised Learning with Graph Gaussian Processes

Top Papers on Clustering Algorithms:

• SLINK: An optimally efficient algorithm for the single-link cluster method
• An efficient algorithm for a complete link method
• Robust Hierarchical Clustering
• Optimal Implementations of UPGMA and Other Common Clustering Algorithms
• An Efficient k-Means Clustering Algorithm: Analysis and Implementation
• A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise
• BIRCH: An Efficient Data Clustering Method for Very Large Databases
• CLARANS: A method for clustering objects for spatial data mining
• FCM: The Fuzzy C-Means Clustering Algorithm
• The Expectation Maximization Algorithm
• The EM Algorithm
• CURE: An Efficient Clustering Algorithm for Large Databases
• A K-Means Clustering Algorithm
• Algorithms for hierarchical clustering: An overview
• Optimal algorithms for complete linkage clustering in d dimensions

5 Latest Research Papers On ML You Must Read:

• Cricket Analytics and Predictor
• Real Time Sleep / Drowsiness Detection
• A Study of Various Text Augmentation Techniques for Relation Classification in Free Text
• Smart Health Monitoring and Management Using Internet of Things, Artificial Intelligence with Cloud Based Processing
• Internet of Things with BIG DATA Analytics − A Survey

Readings in Databases:

• The Five-Minute Rule Ten Years Later, and Other Computer Storage Rules of Thumb
• AlphaSort: A Cache-Sensitive Parallel External Sort
• ARIES: A Transaction Recovery Method Supporting Fine-Granularity Locking and Partial Rollbacks Using Write-Ahead Logging
• Bigtable: A Distributed Storage System for Structured Data
• Efficient Locking for Concurrent Operations on B-Trees
• CAP Twelve Years Later: How the "Rules" Have Changed
• Chord: A Scalable Peertopeer Lookup Service for Internet Applications
• A View of Cloud Computing
• Relational Model of Data for Large Shared Data Banks
• Column-Stores vs. RowStores: How Different Are They Really?
• C-Store: A Column-oriented DBMS
• The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines
• Dremel: Interactive Analysis of WebScale Datasets
• Dynamo: Amazon's Highly Available Key-value Store
• Eddies: Continuously Adaptive Query Processing
• Architecture of a Database System
• The Google File System
• What Goes Around Comes Around
• MapReduce: Simplified Data Processing on Large Clusters
• On Optimistic Methods for Concurrency Control
• Patience is a Virtue: Revisiting Merge and Sort on Modern Processors
• Paxos Made Simple
• In Search of an Understandable Consensus Algorithm (Extended Version)
• The R*-tree: An Efficient and Robust Access Method for Points and Rectangles+
• Shark: SQL and Rich Analytics at Scale
• Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing
• A History and Evaluation of System R
• Access Path Selection in a Relational Database Management System
• Reflections on Trusting Trust
• Improved Query Performance with Variant Indexes
• The Vertica Analytic Database: C-Store 7 Years Later

The 5 Best Data Science Books for Non-Techies:

• Data Science for Business: What You Need to Know about Data Mining and Data-Analytic Thinking
• The Analytics Revolution: How to Improve Your Business By Making Analytics Operational In The Big Data Era
• Executive Data Science: A Guide to Training and Managing the Best Data Scientists
• Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie, or Die
• The Big Data-Driven Business: How to Use Big Data to Win Customers, Beat Competitors, and Boost Profits

Five Must-Read Statistics Books to Become a Successful Data Analyst:

• naked statistics: Stripping the Dread from the Data
• The Signal and the Noise: Why So Many Predictions Fail − but Some Don't
• All of Statistics: A Concise Course in Statistical Inference
• Statistics in Plain English
• Practical Statistics for Data Scientists: 50 Essential Concepts

Deep Learning Papers:

• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Baby Talk: Understanding and Generating Image Descriptions
• Perceptual Losses for Real-Time Style Transfer and Super-Resolution
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Colorful Image Colorization
• Modeling and Propagating CNNs in a Tree Structure for Visual Tracking
• Deep Fragment Embeddings for Bidirectional Image Sentence Mapping
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Generative Visual Manipulation on the Natural Image Manifold
• Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection
• Controlling Perceptual Factors in Neural Style Transfer
• A Neural Algorithm of Artistic Style
• Instance-sensitive Fully Convolutional Networks
• End-to-End Training of Deep Visuomotor Policies
• Decoupled Neural Interfaces using Synthetic Gradients
• Low-shot Visual Recognition by Shrinking and Hallucinating Features
• You Only Look Once: Unified, Real-Time Object Detection
• Deep Visual-Semantic Alignments for Generating Image Descriptions
• Learning to Navigate in Complex Environments
• Human-level control through deep reinforcement learning
• Learning a Recurrent Visual Representation for Image Caption Generation
• Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search
• Progressive Neural Networks
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Instance-aware Semantic Segmentation via Multi-task Network Cascades
• Auto-Encoding Variational Bayes
• Conditional Image Generation with PixelCNN Decoders
• Evolving Large-Scale Neural Networks for Vision-Based Reinforcement Learning
• Generating Sequences With Recurrent Neural Networks
• Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning
• From Captions to Visual Concepts and Back
• Building High-level Features Using Large Scale Unsupervised Learning
• Pixel Recurrent Neural Networks
• Matching Networks for One Shot Learning
• Dropout: A Simple Way to Prevent Neural Networks from Overfitting
• Fully Convolutional Networks for Semantic Segmentation
• Long-term Recurrent Convolutional Networks for Visual Recognition and Description
• Learning to learn by gradient descent by gradient descent
• Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artwork
• SSD: Single Shot MultiBox Detector
• Learning to Segment Object Candidates
• Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
• Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates
• Learning to Track at 100 FPS with Deep Regression Networks
• Asynchronous Methods for Deep Reinforcement Learning
• One-shot Learning with Memory-Augmented Neural Networks
• Transferring Rich Feature Hierarchies for Robust Visual Tracking
• Deep learning
• Rich feature hierarchies for accurate object detection and semantic segmentation
• Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
• Fully-Convolutional Siamese Networks for Object Tracking
• DRAW: A Recurrent Neural Network For Image Generation
• Learning a Deep Compact Image Representation for Visual Tracking
• Human-level concept learning through probabilistic program induction
• Continuous Deep Q-Learning with Model-based Acceleration
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Improving neural networks by preventing co-adaptation of feature detectors
• Siamese Neural Networks for One-Shot Image Recognition
• ImageNet Classification with Deep Convolutional Neural Networks
• Neural Turing Machines
• Going Deeper with Convolutions
• Deep Neural Networks for Object Detection
• Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
• Sim-to-Real Robot Learning from Pixels with Progressive Nets
• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
• Visual Tracking with Fully Convolutional Networks
• Trust Region Policy Optimization
• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• Deep Residual Learning for Image Recognition
• A Fast Learning Algorithm for Deep Belief Nets
• Policy Distillation
• Dueling Network Architectures for Deep Reinforcement Learning
• A Character-Level Decoder without Explicit Segmentation for Neural Machine Translation
• Show and Tell: A Neural Image Caption Generator
• Continuous control with deep reinforcement learning
• Deep Neural Networks for Acoustic Modeling in Speech Recognition
• Layer Normalization
• Adam: A Method for Stochastic Optimization
• Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning
• End-To-End Memory Networks
• Generative Adversarial Nets
• On the importance of initialization and momentum in deep learning
• Playing Atari with Deep Reinforcement Learning
• Fully Character-Level Neural Machine Translation without Explicit Segmentation
• Pointer Networks
• Speech Recognition with Deep Recurrent Neural Networks
• Neural Machine Translation by Jointly Learning to Align and Translate
• Towards End-to-End Speech Recognition with Recurrent Neural Networks
• Every Picture Tells a Story: Generating Sentences from Images
• Deep Learning of Representations for Unsupervised and Transfer Learning
• Joint Learning of Words and Meaning Representations for Open-Text Semantic Parsing
• Reducing the Dimensionality of Data with Neural Networks
• Fast and Accurate Recurrent Neural Network Acoustic Models for Speech Recognition
• Achieving Human Parity in Conversational Speech Recognition
• Effective Approaches to Attention-based Neural Machine Translation
• Memory Networks
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Reinforcement Learning Neural Turing Machines
• Neural Machine Translation of Rare Words with Subword Units
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Sequence to Sequence Learning with Neural Networks
• Addressing the Rare Word Problem in Neural Machine Translation
• Sequence to Sequence Learning with Neural Networks
• Distributed Representations ofWords and Phrases and their Compositionality
• Distilling the Knowledge in a Neural Network
• A Neural Conversational Model
• A Learned Representation For Artistic Style

Research Papers on Programming Languages:

• Linear Logic
• Gradual Typing for Functional Languages
• Soft Typing
• Linear Types Can Change The World!
• Separation Logic and Abstraction
• Separation Logic, Abstraction and Inheritance
• An Object-Oriented Effects System
• A Type System for Borrowing Permissions
• A Certified Type-Preserving Compiler from Lambda Calculus to Assembly Language
• Promises: Limited Specifications for Analysis and Manipulation
• Gradual Typing for Objects
• Capabilities for Uniqueness and Borrowing
• A Verified Compiler for an Impure Functional Language
• Data groups: Specifying the modification of extended state
• Separation and Information Hiding
• Separation Logic: A Logic for SharedMutable Data Structures
• Modular Typestate Checking of Aliased Objects

Numenta Research Papers:

• Evaluating Real-time Anomaly Detection Algorithms – the Numenta Anomaly Benchmark
• Why Neurons Have Thousands of Synapses, A Theory of Sequence Memory in Neocortex
• How Can We Be So Dense? The Benefits of Using Highly Sparse Representations
• A Theory of How Columns in the Neocortex Enable Learning the Structure of the World
• Unsupervised real-time anomaly detection for streaming data
• Locations in the Neocortex: A Theory of Sensorimotor Object Recognition Using Cortical Grid Cells
• The HTM Spatial Pooler — A Neocortical Algorithm for Online Sparse Distributed Coding

Awesome Machine Learning Papers:

• Binarized Neural Networks: Training Neural Networks withWeights and Activations Constrained to +1 or -1
• Value Iteration Networks
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
• Composing graphical models with neural networks for structured representations and fast inference
• Supervised Learning With Quantum-Inspired Tensor Networks
• Fast ε-free Inference of Simulation Models with Bayesian Conditional Density Estimation
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Unsupervised Learning for Physical Interaction through Video Prediction
• Data Programming: Creating Large Training Sets, Quickly
• Convolutional Neural Fabrics
• Generative Adversarial Imitation Learning
• Learning to learn by gradient descent by gradient descent
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• Using Fast Weights to Attend to the Recent Past
• Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences
• Full-Capacity Unitary Recurrent Neural Networks
• Stochastic Variational Deep Kernel Learning
• PVANet: Lightweight Deep Neural Networks for Real-time Object Detection
• Interpretable Distribution Features with Maximum Testing Power
• Fast and Provably Good Seedings for k-Means
• Adversarial Multiclass Classification: A Risk Minimization Perspective
• Bayesian Optimization for Probabilistic Programs

3D Detection Papers:

The papers in this list are about Autonomous Vehicles 3D Detection and  Semantic Segmentation especially those using point clouds and in deep learning methods.

---

• FusionNet: 3D Object Classification Using Multiple Data Representations
• Vehicle Detection from 3D Lidar Using Fully Convolutional Network
• Multi-View 3D Object Detection Network for Autonomous Driving
• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
• Frustum PointNets for 3D Object Detection from RGB-D Data
• PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation
• Joint 3D Proposal Generation and Object Detection from View Aggregation
• Recurrent Slice Networks for 3D Segmentation of Point Clouds
• A General Pipeline for 3D Detection of Vehicles
• PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation
• RoarNet: A Robust 3D Object Detection based on RegiOn Approximation Refinement
• PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
• IPOD: Intensive Point-based Object Detector for Point Cloud
• PointPillars: Fast Encoders for Object Detection from Point Clouds
• Three-dimensional Backbone Network for 3D Object Detection in Traffic Scenes
• PIXOR: Real-time 3D Object Detection from Point Clouds
• Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression
• Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection
• Part-A² Net: 3D Part-Aware and Aggregation Neural Network for Object Detection from Point Cloud
• Voxel-FPN: multi-scale voxel feature aggregation in 3D object detection from point clouds
• STD: Sparse-to-Dense 3D Object Detector for Point Cloud
• Fast Point R-CNN
• MLOD: A multi-view 3D object detection based on robust feature fusion method
• Patch Refinement - Localized 3D Object Detection
• PI-RCNN: An Efficient Multi-sensor 3D Object Detector with Point-based Attentive Cont-conv Fusion Module
• SCNet: Subdivision Coding Network for Object Detection Based on 3D Point Cloud
• Sliding Shapes for 3D Object Detection in Depth Images
• VoxNet: A 3D Convolutional Neural Network for Real-Time Object Recognition
• 3d fully convolutional network for vehicle detection in point cloud
• Voting for Voting in Online Point Cloud Object Detection
• Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks
• OctNet: Learning Deep 3D Representations at High Resolutions
• Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images
• SECOND: Sparsely Embedded Convolutional Detection
• Multiview Random Forest of Local Experts Combining RGB and LIDAR data for Pedestrian Detection
• Multi-Task Multi-Sensor Fusion for 3D Object Detection
• Deep Continuous Fusion for Multi-Sensor 3D Object Detection
• Pedestrian detection combining RGB and dense LIDAR data
• Volumetric and Multi-View CNNs for Object Classification on 3D Data
• PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
• 3D-Assisted Feature Synthesis for Novel Views of an Object
• Multi-view Convolutional Neural Networks for 3D Shape Recognition

Ten Trending Academic Papers on the Future of Computer Vision:

• Learning Individual Styles of Conversational Gesture
• Textured Neural Avatars
• DSFD: Dual Shot Face Detector
• GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction
• DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images
• Inverse Cooking: Recipe Generation from Food Images
• ArcFace: Additive Angular Margin Loss for Deep Face Recognition
• Fast Online Object Tracking and Segmentation: A Unifying Approach
• Revealing Scenes by Inverting Structure from Motion Reconstructions
• Semantic Image Synthesis with Spatially-Adaptive Normalization

Must-Read Papers on GANs:

Generative Adversarial Networks are one of the most interesting and popular applications of Deep Learning. Here are the list of 10 papers on GANs that will give you a great introduction to GAN as well as a foundation for understanding the state-of-the-art. 

---

• Generative Adversarial Nets
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Improved Techniques for Training GANs
• Image-to-Image Translation with Conditional Adversarial Networks
• StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• A Style-Based Generator Architecture for Generative Adversarial Networks

5 Must-read Papers on Product Categorization for Data Scientists:

• Don't Classify, Translate: Multi-Level E-Commerce Product Categorization Via Machine Translation
• Large-Scale Categorization of Japanese Product Titles Using Neural Attention Models
• Atlas: A Dataset and Benchmark for E-commerce Clothing Product Categorization
• Large Scale Product Categorization using Structured and Unstructured Attributes
• Multi-Label Product Categorization Using Multi-Modal Fusion Models

Must read research papers on Data Structures:

• Making data structures persistent (1986)
• Fractional cascading: A data structuring technique (1986)
• Ordered Hash Table (1973)
• Randomized Search Trees (1989)
• EERTREE: An Efficient Data Structure for Processing Palindromes in Strings (2015)

Key Papers in Deep RL:

---

Model-Free RL:

Deep Q-Learning

---

• Playing Atari with Deep Reinforcement Learning
• Deep Recurrent Q-Learning for Partially Observable MDPs
• Dueling Network Architectures for Deep Reinforcement Learning
• Deep Reinforcement Learning with Double Q-learning
• Prioritized Experience Replay
• Rainbow: Combining Improvements in Deep Reinforcement Learning

Policy Gradients

---

• Asynchronous Methods for Deep Reinforcement Learning
• Trust Region Policy Optimization
• High-Dimensional Continuous Control Using Generalized Advantage Estimation
• Emergence of Locomotion Behaviours in Rich Environments
• Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
• Sample Efficient Actor-Critic with Experience Replay
• Proximal Policy Optimization Algorithms
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor

Deterministic Policy Gradients

---

• Deterministic Policy Gradient Algorithms
• Continuous Control With Deep Reinforcement Learning
• Addressing Function Approximation Error in Actor-Critic Methods

Distributional RL

---

• A Distributional Perspective on Reinforcement Learning
• Distributional Reinforcement Learning with Quantile Regression
• Implicit Quantile Networks for Distributional Reinforcement Learning
• Dopamine: A Research Framework for Deep Reinforcement Learning

Policy Gradients with Action-Dependent Baselines

---

• Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic
• Action-depedent Control Variates for Policy Optimization via Stein's Identity
• The Mirage of Action-Dependent Baselines in Reinforcement Learning

Path-Consistency Learning

---

• Bridging the Gap Between Value and Policy Based Reinforcement Learning
• Trust-PCL: An Off-Policy Trust Region Method for Continuous Control

Other Directions for Combining Policy-Learning and Q-Learning

---

• Combining Policy Gradient and Q-learning
• The Reactor: A Fast and Sample-Efficient Actor-Critic Agent for Reinforcement Learning
• Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement LearningBridging the Gap Between Value and Policy Based Reinforcement Learning
• Equivalence Between Policy Gradients and Soft Q-Learning

Evolutionary Algorithms

---

• Evolution Strategies as a Scalable Alternative to Reinforcement Learning

Exploration:

Intrinsic Motivation

---

• VIME: Variational Information Maximizing Exploration
• Unifying Count-Based Exploration and Intrinsic Motivation
• #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
• EX²: Exploration with Exemplar Models for Deep Reinforcement Learning
• Count-Based Exploration with Neural Density Models
• Curiosity-driven Exploration by Self-supervised Prediction
• Large-Scale Study of Curiosity-Driven Learning
• Exploration by Random Network Distillation

Unsupervised RL

---

• Variational Intrinsic Control
• Diversity is All You Need: Learning Skills without a Reward Function
• Variational Option Discovery Algorithms

Transfer and Multitask RL:

• Progressive Neural Networks
• Reinforcement Learning with Unsupervised Auxiliary Tasks
• PathNet: Evolution Channels Gradient Descent in Super Neural Networks
• Hindsight Experience Replay
• The Intentional Unintentional Agent: Learning to Solve Many Continuous Control Tasks Simultaneously
• Learning an Embedding Space for Transferable Robot Skills
• Universal Value Function Approximators
• Mutual Alignment Transfer Learning

Hierarchy:

• Strategic Attentive Writer for Learning Macro-Actions
• FeUdal Networks for Hierarchical Reinforcement Learning
• Data-Efficient Hierarchical Reinforcement Learning

Memory:

• Model-Free Episodic Control
• Neural Map: Structured Memory for Deep Reinforcement Learning
• Neural Episodic Control
• Unsupervised Predictive Memory in a Goal-Directed Agent
• Relational recurrent neural networks

Model-Based RL:

Model is Learned

---

• Imagination-Augmented Agents for Deep Reinforcement Learning
• Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning
• Model-Based Value Expansion for Efficient Model-Free Reinforcement Learning
• Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion
• Recurrent World Models Facilitate Policy Evolution
• Model-Based Reinforcement Learning via Meta-Policy Optimization
• Model-Ensemble Trust-Region Policy Optimization

Model is Given

---

• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Thinking Fast and Slow with Deep Learning and Tree Search

Meta-RL:

• RL²: Fast Reinforcement Learning via Slow Reinforcement Learning
• Learning to Reinforcement Learn
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• A Simple Neural Attentive Meta-Learner

Scaling RL:

• Accelerated Methods for Deep Reinforcement Learning
• Distributed Prioritized Experience Replay
• Recurrent Experience Replay in Distributed Reinforcement Learning
• RLlib: Abstractions for Distributed Reinforcement Learning
• IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures

RL in the Real World:

• Benchmarking Reinforcement Learning Algorithms on Real-World Robots
• Horizon: Facebook's Open Source Applied Reinforcement Learning Platform
• Learning Dexterous In-Hand Manipulation
• QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation

Safety:

• Concrete Problems in AI Safety
• Constrained Policy Optimization
• Deep Reinforcement Learning from Human Preferences
• Trial without Error: Towards Safe Reinforcement Learning via Human Intervention
• Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning
• Safe Exploration in Continuous Action Spaces

Imitation Learning and Inverse Reinforcement Learning:

• Generative Adversarial Imitation Learning
• DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skill
• Modeling Purposeful Adaptive Behavior with the Principle of Maximum Causal Entropy
• Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
• Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization
• One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL

Reproducibility, Analysis, and Critique:

• Benchmarking Deep Reinforcement Learning for Continuous Control
• Simple random search provides a competitive approach to reinforcement learning
• Where Did My Optimum Go?: An Empirical Analysis of Gradient Descent Optimization in Policy Gradient Methods
• Are Deep Policy Gradient Algorithms Truly Policy Gradient Algorithms?
• Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control
• Benchmarking Model-Based Reinforcement Learning
• Deep Reinforcement Learning that Matters

Bonus: Classic Papers in RL Theory or Review:

• Policy Gradient Methods for Reinforcement Learning with Function Approximation
• An Analysis of Temporal-Difference Learning with Function Approximation
• Approximately Optimal Approximate Reinforcement Learning
• A Natural Policy Gradient
• Algorithms for Reinforcement Learning
• Reinforcement Learning of Motor Skills with Policy Gradients

14 NLP Research Breakthroughs You Can Apply To Your Business:

• Universal Language Model Fine-tuning for Text Classification
• Deep contextualized word representations
• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• Phrase-Based and Neural Unsupervised Machine Translation
• Linguistically-Informed Self-Attention for Semantic Role Labeling
• What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties
• Know What You Don't Know: Unanswerable Questions for SQuAD
• Swag: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference
• Meta-Learning for Low-Resource Neural Machine Translation
• Dissecting ContextualWord Embeddings: Architecture and Representation
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
• A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks
• Sequence classification with human attention
• Improving Language Understanding by Generative Pre-Training

Most Downloaded Artificial Intelligence Articles:

• Artificial cognition for social human–robot interaction: An implementation
• Explanation in artificial intelligence: Insights from the social sciences
• Creativity and artificial intelligence
• Quantum computation, quantum theory and AI
• Argumentation in artificial intelligence
• Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
• Selection of relevant features and examples in machine learning
• Unsupervised human activity analysis for intelligent mobile robots
• Evolution of artificial intelligence
• Robot ethics: Mapping the issues for a mechanized world
• Determining inference semantics for disjunctive logic programs
• The dropout learning algorithm
• Conflict-based search for optimal multi-agent pathfinding
• Wrappers for feature subset selection
• Integrating social power into the decision-making of cognitive agents
• Learning multilingual named entity recognition from Wikipedia
• Algorithm Runtime Prediction: Methods and Evaluation
• Hidden semi-Markov models
• Shifting viewpoints: Artificial intelligence and human–computer interaction
• Multiple instance classification: Review, taxonomy and comparative study
• Watson: Beyond Jeopardy!
• Human-level artificial general intelligence and the possibility of a technological singularity A reaction to Ray Kurzweil's The Singularity Is Near, and McDermott's critique of Kurzweil
• Distributional semantics of objects in visual scenes incomparison totext
• Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach
• Planning and acting in partially observable stochastic domains

AI Papers and Notes:

• Deep multi-scale video prediction beyond mean square error
• Policy Distillation
• Asynchronous Methods for Deep Reinforcement Learning
• Causal models for data-driven debugging and decision making in cloud computing
• Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
• COCO-Stuff: Thing and Stuff Classes in Context
• Beyond Bilinear: Generalized Multimodal Factorized High-order Pooling for Visual Question Answering
• ConvNet Architecture Search for Spatiotemporal Feature Learning
• ByRDiE: Byzantine-resilient Distributed Coordinate Descent for Decentralized Learning
• Dynamic Routing Between Capsules
• A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning
• MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks
• Single-Shot Refinement Neural Network for Object Detection
• Self-Supervised Vision-Based Detection of the Active Speaker as Support for Socially-Aware Language Acquisition
• A Multi-Horizon Quantile Recurrent Forecaster
• Compressed Video Action Recognition
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
• Learning Deep Features for One-Class Classification
• A Two-Stage Method for Text Line Detection in Historical Documents
• Deep contextualized word representations
• The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
• The ApolloScape Open Dataset for Autonomous Driving and its Application
• Actor and Action Video Segmentation from a Sentence
• Pose2Seg: Detection Free Human Instance Segmentation
• Meta-Learning Update Rules for Unsupervised Representation Learning
• Stochastic Adversarial Video Prediction
• Learning Latent Events from Network Message Logs
• Asynch-SGBDT: Train a Stochastic Gradient Boosting Decision Tree in an Asynchronous Parallel Manner
• ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector
• QuaterNet: A Quaternion-based Recurrent Model for Human Motion
• AutoAugment: Learning Augmentation Strategies from Data
• Double Quantization for Communication-Efficient Distributed Optimization
• PipeDream: Fast and Efficient Pipeline Parallel DNN Training
• Hierarchical Long-term Video Prediction without Supervision
• Neural Ordinary Differential Equations
• Restructuring Batch Normalization to Accelerate CNN Training
• Adaptive Neural Trees
• MnasNet: Platform-Aware Neural Architecture Search for Mobile
• Scene-LSTM: A Model for Human Trajectory Prediction
• Mitigating Sybils in Federated Learning Poisoning
• Trick Me If You Can: Human-in-the-loop Generation of Adversarial Examples for Question Answering
• Deep learning for time series classification: a review
• Autonomous Exploration, Reconstruction, and Surveillance of 3D Environments Aided by Deep Learning
• Faster Training of Mask R-CNN by Focusing on Instance Boundaries
• Machine Learning for Forecasting Mid Price Movement using Limit Order Book Data
• On-field player workload exposure and knee injury risk monitoring via deep learning
• Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks
• Real-time Dynamic Object Detection for Autonomous Driving using Prior 3D-Maps
• Mini-batch Serialization: CNN Training with Inter-layer Data Reuse
• Representation Flow for Action Recognition
• A Comprehensive Survey of Deep Learning for Image Captioning
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
• Distributed Learning over Unreliable Networks
• Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD
• A Modern Take on the Bias-Variance Tradeoff in Neural Networks
• What can AI do for me?
• Democratizing Production-Scale Distributed Deep Learning
• SocialGCN: An Efficient Graph Convolutional Network based Model for Social Recommendation
• Federated Learning for Mobile Keyboard Prediction
• Deep Object-Centric Policies for Autonomous Driving
• Show, Attend and Translate: Unpaired Multi-Domain Image-to-Image Translation with Visual Attention
• Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics
• Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints
• TSM: Temporal Shift Module for Efficient Video Understanding
• Recent Advances in Open Set Recognition: A Survey
• 50 Years of Test (Un)fairness: Lessons for Machine Learning
• Optimized Skeleton-based Action Recognition via Sparsified Graph Regression
• Neural Separation of Observed and Unobserved Distributions
• Deep Learning based Pedestrian Detection at Distance in Smart Cities
• Bag of Tricks for Image Classification with Convolutional Neural Networks
• Learning 3D Human Dynamics from Video
• A Structured Model For Action Detection
• Deep Learning on Graphs: A SurveyHow to make ad-hoc polymorphism less ad hoc
• PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
• Graph Neural Networks: A Review of Methods and Applications
• Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling
• Scale-Aware Trident Networks for Object Detection
• Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
• RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free
• Self-Driving Cars: A Survey
• Toward Explainable Fashion Recommendation
• The autofeat Python Library for Automated Feature Engineering and Selection
• Revisiting Self-Supervised Visual Representation Learning
• Progressive Image Deraining Networks: A Better and Simpler Baseline
• DistInit: Learning Video RepresentationsWithout a Single Labeled Video
• Fixup Initialization: Residual Learning Without Normalization
• The Evolved Transformer
• Dataset Culling: Towards Efficient Training Of Distillation-Based Domain Specific Models
• TF-Replicator: Distributed Machine Learning for Researchers
• Augmented Autoencoders: Implicit 3D Orientation Learning for 6D Object Detection
• An Effective Approach to Unsupervised Machine Translation
• NeurAll: Towards a Unified Visual Perception Model for Automated Driving
• MOTS: Multi-Object Tracking and Segmentation
• Hierarchical Graph Convolutional Networks for Semi-supervised Node Classification
• DNNVM : End-to-End Compiler Leveraging Heterogeneous Optimizations on FPGA-based CNN Accelerators
• Cascade Feature Aggregation for Human Pose Estimation
• Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
• Online Meta-Learning
• Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression
• Diagnosing Bottlenecks in Deep Q-learning Algorithms
• Accelerating Self-Play Learning in Go
• Efficient Video Classification Using Fewer Frames
• Provable Guarantees for Gradient-Based Meta-Learning
• Towards Robust ResNet: A Small Step but A Giant Leap
• BERT for Joint Intent Classification and Slot Filling
• DPOD: 6D Pose Object Detector and Refiner
• A Generative Map for Image-based Camera Localization
• Speeding up Deep Learning with Transient Servers
• Video Summarization via Actionness Ranking
• Video Extrapolation with an Invertible Linear Embedding
• Characterizing Activity on the Deep and DarkWeb
• Mask Scoring R-CNN
• Crowding in humans is unlike that in convolutional neural networks
• Continuous Integration of Machine Learning Models with ease. ml/ci: Towards a Rigorous Yet Practical Treatment
• Visual-based Autonomous Driving Deployment from a Stochastic and Uncertainty-aware Perspective
• VideoFlow: A Flow-Based Generative Model for Video
• Stabilizing the Lottery Ticket Hypothesis
• Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases inWord Embeddings But do not Remove Them
• Activation Analysis of a Byte-Based Deep Neural Network for Malware Classification
• An End-to-End Network for Panoptic Segmentation
• All You Need is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image Classification
• Two-Stream Action Recognition-Oriented Video Super-Resolution
• SimpleDet: A Simple and Versatile Distributed Framework for Object Detection and Instance Recognition
• BLVD: Building A Large-scale 5D Semantics Benchmark for Autonomous Driving
• Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection
• Adversarial Networks for Camera Pose Regression and Refinement
• Fast Interactive Object Annotation with Curve-GCN
• Real time backbone for semantic segmentation
• AttoNets: Compact and Efficient Deep Neural Networks for the Edge via Human-Machine Collaborative Design
• IvaNet: Learning to jointly detect and segment objets with the help of Local Top-Down Modules
• Understanding the Limitations of CNN-based Absolute Camera Pose Regression
• Scaling Human Activity Recognition to edge devices
• Learning Correspondence from the Cycle-consistency of Time
• Cloze-driven Pretraining of Self-attention Networks
• Simple, Fast, Accurate Intent Classification and Slot Labeling for Goal-Oriented Dialogue Systems
• In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images
• Segmentation-Based Deep-Learning Approach for Surface-Defect Detection
• LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving
• Progressive Sparse Local Attention for Video Object Detection
• Coin.AI: A Proof-of-Useful-Work Scheme for Blockchain-Based Distributed Deep Learning
• Data Poisoning against Differentially-Private Learners: Attacks and Defenses
• Looking Fast and Slow: Memory-Guided Mobile Video Object Detection
• Robust Neural Networks using Randomized Adversarial Training
• MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning
• Fine-tune BERT for Extractive Summarization
• ShopSign: a Diverse Scene Text Dataset of Chinese Shop Signs in Street Views
• Few-Shot Learning-Based Human Activity Recognition
• Video Relationship Reasoning using Gated Spatio-Temporal Energy Graph
• Reducing the dilution: An analysis of the information sensitiveness of capsule network with a practical improvement method
• Improving image classifiers for small datasets by learning rate adaptations
• FVNet: 3D Front-View Proposal Generation for Real-Time Object Detection from Point Clouds
• Large-scale interactive object segmentation with human annotators
• GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving
• Simple Applications of BERT for Ad Hoc Document Retrieval
• DetNAS: Backbone Search for Object Detection
• nuScenes: A multimodal dataset for autonomous driving
• Hearing your touch: A new acoustic side channel on smartphones
• Training Quantized Neural Networks with the Full-precision Auxiliary Module
• Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methods
• Scalable Deep Learning on Distributed Infrastructures: Challenges, Techniques and Tools
• Dense Intrinsic Appearance Flow for Human Pose Transfer
• Self-Supervised Learning via Conditional Motion Propagation
• Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving
• ThunderNet: Towards Real-time Generic Object Detection
• Pyramid Mask Text Detector
• FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation
• Distilling Task-Specific Knowledge from BERT into Simple Neural Networks
• Fast video object segmentation with Spatio-Temporal GANs
• TensorMask: A Foundation for Dense Object Segmentation
• Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
• Yet Another Accelerated SGD: ResNet-50 Training on ImageNet in 74.7 seconds
• Interpreting Black Box Models via Hypothesis Testing
• Video Object Segmentation using Space-Time Memory Networks
• Res2Net: A New Multi-scale Backbone Architecture
• Habitat: A Platform for Embodied AI Research
• Fence GAN: Towards Better Anomaly Detection
• HoloGAN: Unsupervised Learning of 3D Representations From Natural Images
• FCOS: Fully Convolutional One-Stage Object Detection
• Exploring Randomly Wired Neural Networks for Image Recognition
• Towards semi-supervised segmentation via image-to-image translation
• VideoBERT: A Joint Model for Video and Language Representation Learning
• Patchwork: A Patch-wise Attention Network for Efficient Object Detection and Segmentation in Video Streams
• Modeling Vocabulary for Big Code Machine Learning
• DADA: Depth-Aware Domain Adaptation in Semantic Segmentation
• DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation
• Spatiotemporal CNN for Video Object Segmentation
• White-to-Black: Efficient Distillation of Black-Box Adversarial Attacks
• Efficient GAN-based method for cyber-intrusion detection
• Signal-to-Noise Ratio: A Robust Distance Metric for Deep Metric Learning
• On Direct Distribution Matching for Adapting Segmentation Networks
• UU-Nets Connecting Discriminator and Generator for Image to Image Translation
• YOLACT: Real-time Instance Segmentation
• A Systematic Literature Review about the impact of Artificial Intelligence on Autonomous Vehicle Safety
• T-Net: Parametrizing Fully Convolutional Nets with a Single High-Order Tensor
• Libra R-CNN: Towards Balanced Learning for Object Detection
• FLightNNs: Lightweight Quantized Deep Neural Networks for Fast and Accurate Inference
• Center and Scale Prediction: A Box-free Approach for Object Detection
• ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors
• Adaptive NMS: Refining Pedestrian Detection in a Crowd
• Speech Model Pre-training for End-to-End Spoken Language Understanding
• FoveaBox: Beyond Anchor-based Object Detector
• Weakly Supervised Person Re-ID: Differentiable Graphical Learning and A New Benchmark
• Referring to Objects in Videos using Spatio-Temporal Identifying Descriptions
• Kervolutional Neural Networks
• Meta Filter Pruning to Accelerate Deep Convolutional Neural Networks
• Weakly Supervised Semantic Segmentation of Satellite Images
• ASAP: Architecture Search, Anneal and Prune
• Accelerated Neural Networks on OpenCL Devices Using SYCL-DNN
• Unsupervised learning of action classes with continuous temporal embedding
• Dynamics of Pedestrian Crossing Decisions Based on Vehicle Trajectories in Large-Scale Simulated and Real-World Data
• Relational Action Forecasting
• A Closer Look at Few-shot Classification
• Rethinking Classification and Localization for Object Detection
• Improving interactive reinforcement learning: What makes a good teacher?
• DuBox: No-Prior Box Objection Detection via Residual Dual Scale Detectors
• Exploiting Event Log Event Attributes in RNN Based Prediction
• Human-Guided Learning of Column Networks: Augmenting Deep Learning with Advice
• LeanResNet: A Low-cost Yet Effective Convolutional Residual Networks
• Painting on Placement: Forecasting Routing Congestion using Conditional Generative Adversarial Nets
• Reinforcement Learning with Probabilistic Guarantees for Autonomous Driving
• End-to-End Robotic Reinforcement Learning without Reward Engineering
• Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotations
• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
• Understanding Neural Networks via Feature Visualization: A survey
• From GAN to WGAN
• Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT
• LATTE: Accelerating LiDAR Point Cloud Annotation via Sensor Fusion, One-Click Annotation, and Tracking
• Code-Switching for Enhancing NMT with Pre-Specified Translation
• SelFlow: Self-Supervised Learning of Optical Flow
• Video Object Segmentation and Tracking: A Survey
• Fashion++: Minimal Edits for Outfit Improvement
• Unifying Question Answering and Text Classification via Span Extraction
• STEP: Spatio-Temporal Progressive Learning for Video Action Detection
• Evaluation Uncertainty in Data-Driven Self-Driving Testing
• Mask-Predict: Parallel Decoding of Conditional Masked Language Models
• Language Models with Transformers
• Neural Architecture Search for Deep Face Recognition
• Automatic Temporally Coherent Video Colorization
• A Simple Pooling-Based Design for Real-Time Salient Object Detection
• Generative Exploration and Exploitation
• BERTScore: Evaluating Text Generation with BERT
• An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection
• The Curious Case of Neural Text Degeneration
• Fast User-Guided Video Object Segmentation by Interaction-and-Propagation Networks
• Real-time Intent Prediction of Pedestrians for Autonomous Ground Vehicles via Spatio-Temporal DenseNet
• Attention Augmented Convolutional Networks
• NeurIPS 2019 Competition: The MineRL Competition on Sample Efficient Reinforcement Learning using Human Priors
• Ethics of Artificial Intelligence Demarcations
• Wasserstein-Fisher-Rao Document Distance
• Generating Long Sequences with Sparse Transformers
• ViDeNN: Deep Blind Video Denoising
• Plug-in, Trainable Gate for Streamlining Arbitrary Neural Networks
• Neural Path Planning: Fixed Time, Near-Optimal Path Generation via Oracle Imitation
• HAR-Net: Joint Learning of Hybrid Attention for Single-stage Object Detection
• LADN: Local Adversarial Disentangling Network for Facial Makeup and De-Makeup
• Decentralized Multi-Task Learning Based on Extreme Learning Machines
• Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation
• The Zero Resource Speech Challenge 2019: TTS without T
• Safe Reinforcement Learning with Scene Decomposition for Navigating Complex Urban Environments
• Making Convolutional Networks Shift-Invariant Again
• Spatial-Temporal Relation Networks for Multi-Object Tracking
• RepPoints: Point Set Representation for Object Detection
• Local Relation Networks for Image Recognition
• GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
• Face Video Generation from a Single Image and Landmarks
• Survey on Automated Machine Learning
• Graph Kernels: A Survey
• Real numbers, data science and chaos: How to fit any dataset with a single parameter
• Deferred Neural Rendering: Image Synthesis using Neural Textures
• DAC: The Double Actor-Critic Architecture for Learning Options
• Graph Matching Networks for Learning the Similarity of Graph Structured Objects
• Adversarial Training for Free!
• Optimal Sparse Decision Trees
• Unsupervised Data Augmentation for Consistency Training
• Challenges of Real-World Reinforcement Learning
• Enabling Robots to Understand Incomplete Natural Language Instructions Using Commonsense Reasoning
• A Study on Action Detection in the Wild
• A critical analysis of self-supervision, or what we can learn from a single image
• Segmentation Is All You Need
• Survey of Dropout Methods for Deep Neural Networks
• Deep Learning for Audio Signal Processing
• AdaNet: A Scalable and Flexible Framework for Automatically Learning Ensembles
• ResNet Can Be Pruned 60×: Introducing Network Purification and Unused Path Removal (P-RM) afterWeight Pruning
• Learn to synthesize and synthesize to learn
• Information-Theoretic Considerations in Batch Reinforcement Learning
• Fast AutoAugment
• Learn Stereo, Infer Mono: Siamese Networks for Self-Supervised, Monocular, Depth Estimation
• Similarity of Neural Network Representations Revisited
• Billion-scale semi-supervised learning for image classification
• 26ms Inference Time for ResNet-50: Towards Real-Time Execution of all DNNs on Smartphone
• Recurrent Convolutional Strategies for Face Manipulation Detection in Videos
• RetinaFace: Single-stage Dense Face Localisation in the Wild
• From Video Game to Real Robot: The Transfer between Action Spaces
• Single Image Portrait Relighting
• Self-supervised Learning for Video Correspondence Flow
• You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle
• Joint High Dynamic Range Imaging and Super-Resolution from a Single Image
• Collaborative Evolutionary Reinforcement Learning
• Anti-Confusing: Region-Aware Network for Human Pose Estimation
• Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask
• Deep Residual Reinforcement Learning
• Seamless Scene Segmentation
• SCOPS: Self-Supervised Co-Part Segmentation
• A Survey on Neural Architecture Search
• SoilingNet: Soiling Detection on Automotive Surround-View Cameras
• Few-Shot Unsupervised Image-to-Image Translation
• FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing
• Fairness-Aware Ranking in Search and Recommendation Systems with Application to LinkedIn Talent Search
• Visibility Constrained Generative Model for Depth-based 3D Facial Pose Tracking
• Batch Normalization is a Cause of Adversarial Vulnerability
• Adversarial Examples Are Not Bugs, They Are Features
• A Geometric Approach to Obtain a Bird’s Eye View from an Image
• Searching for MobileNetV3
• MixMatch: A Holistic Approach to Semi-Supervised Learning
• Gaussian Differential Privacy
• LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation
• MASS: Masked Sequence to Sequence Pre-training for Language Generation
• Trinity of Pixel Enhancement: a Joint Solution for Demosaicking, Denoising and Super-Resolution
• A Comprehensive Analysis on Adversarial Robustness of Spiking Neural Networks
• Understanding Attention and Generalization in Graph Neural Networks
• Deep Flow-Guided Video Inpainting
• Multimodal Semantic Attention Network for Video Captioning
• Meta-learning of Sequential Strategies
• Thinking Outside the Box: Generation of Unconstrained 3D Room Layouts
• Unified Language Model Pre-training for Natural Language Understanding and Generation
• End-to-End Wireframe Parsing
• Universal Sound Separation
• PPGNet: Learning Point-Pair Graph for Line Segment Detection
• Embedding Human Knowledge into Deep Neural Network via Attention Map
• Learning Loss for Active Learning
• What Do Single-view 3D Reconstruction Networks Learn?
• Processing Megapixel Images with Deep Attention-Sampling Models
• The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study
• Legal Judgment Prediction via Multi-Perspective Bi-Feedback Network
• Survey on Evaluation Methods for Dialogue Systems
• EdgeSegNet: A Compact Network for Semantic Segmentation
• Language Modeling with Deep Transformers
• Neuroscore: A Brain-inspired Evaluation Metric for Generative Adversarial Networks
• Mega-Reward: Achieving Human-Level Play without Extrinsic Rewards
• NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
• Video Instance Segmentation
• ISBNet: Instance-aware Selective Branching Network
• BayesNAS: A Bayesian Approach for Neural Architecture Search
• Few-Shot Viewpoint Estimation
• Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
• Object Detection in 20 Years: A Survey
• VideoGraph: Recognizing Minutes-Long Human Activities in Videos
• Zoom to Learn, Learn to Zoom
• Graph U-Nets
• A Context-and-Spatial Aware Network for Multi-Person Pose Estimation
• A Survey of Multilingual Neural Machine Translation
• Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection
• Cognitive Graph for Multi-Hop Reading Comprehension at Scale
• Entity-Relation Extraction as Multi-turn Question Answering
• How to Fine-Tune BERT for Text Classification?
• Efficient Ladder-style DenseNets for Semantic Segmentation of Large Images
• Sparse Sequence-to-Sequence Models
• Machine Learning at Microsoft with ML.NET
• Graph Convolutional Gaussian Processes
• Learnable Triangulation of Human Pose
• DARNet: Deep Active Ray Network for Building Segmentation
• Transferable Clean-Label Poisoning Attacks on Deep Neural Nets
• Learning What and Where to Transfer
• Task-Driven Modular Networks for Zero-Shot Compositional Learning
• Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks
• Automated detection of business-relevant outliers in e-commerce conversion rate
• BERT Rediscovers the Classical NLP Pipeline
• Learning Active Spine Behaviors for Dynamic and Efficient Locomotion in Quadruped Robots
• Dual Supervised Learning for Natural Language Understanding and Generation
• Neural Query Language: A Knowledge Base Query Language for Tensorflow
• GMNN: Graph Markov Neural Networks
• 3D Semantic Scene Completion from a Single Depth Image using Adversarial Training
• A Human-Centered Approach to Interactive Machine Learning
• 3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions
• What do you learn from context? Probing for sentence structure in contextualized word representations
• Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images
• IPC: A Benchmark Data Set for Learning with Graph-Structured Data
• Improved Safe Real-time Heuristic Search
• Meta reinforcement learning as task inference
• Dynamic Neural Network Channel Execution for Efficient Training
• An interdisciplinary survey of network similarity methods
• Semi-supervised learning based on generative adversarial network: a comparison between good GAN and bad GAN approach
• ReshapeGAN: Object Reshaping by Providing A Single Reference Image
• ncRNA Classification with Graph Convolutional Networks
• Meta Reinforcement Learning with Task Embedding and Shared Policy
• FH-GAN: Face Hallucination and Recognition using Generative Adversarial Network
• HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization
• On Conditioning GANs to Hierarchical Ontologies
• MoGlow: Probabilistic and controllable motion synthesis using normalising flows
• Latent Universal Task-Specific BERT
• Robust Real-time Pedestrian Detection in Aerial Imagery on Jetson TX2
• Effective Sentence Scoring Method using Bidirectional Language Model for Speech Recognition
• Vision-based Robotic Grasping from Object Localization, Pose Estimation, Grasp Detection to Motion Planning: A Review
• Inferring Javascript types using Graph Neural Networks
• Autonomous Vehicle Control: End-to-end Learning in Simulated Urban Environments
• BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning
• Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation
• Harvesting Information from Captions forWeakly Supervised Semantic Segmentation
• Behavior Sequence Transformer for E-commerce Recommendation in Alibaba
• Learning Discriminative Features in Sequence Training without Requiring Framewise Labelled Data
• Deep Learning for Multi-Scale Changepoint Detection in Multivariate Time Series
• Fooling Computer Vision into Inferring theWrong Body Mass Index
• Monocular Plan View Networks for Autonomous Driving
• The Materials Science Procedural Text Corpus: Annotating Materials Synthesis Procedures with Shallow Semantic Structures
• How do neural networks see depth in single images?
• ERNIE: Enhanced Language Representation with Informative Entities
• Training Object Detectors With Noisy Data
• AM-LFS: AutoML for Loss Function Search
• Learning to Reconstruct 3D Manhattan Wireframes from a Single Image
• Which Tasks Should Be Learned Together in Multi-task Learning?
• Learning Video Representations from Correspondence Proposals
• PaperRobot: Incremental Draft Generation of Scientific Ideas
• Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
• Towards Neural Decompilation
• GAPNet: Graph Attention based Point Neural Network for Exploiting Local Feature of Point Cloud
• Lightweight Network Architecture for Real-Time Action Recognition
• RIU-Net: Embarrassingly simple semantic segmentation of 3D LiDAR point cloud
• Semi-Supervised Learning with Scarce Annotations
• The Machine Learning Bazaar: Harnessing the ML Ecosystem for Effective System Development
• ATTENTIONRNN: A Structured Spatial Attention Mechanism
• Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned
• Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
• Speech2Face: Learning the Face Behind a Voice
• Light-Weight RetinaNet for Object Detection
• OVSNet : Towards One-Pass Real-Time Video Object Segmentation
• N-BEATS: Neural basis expansion analysis for interpretable time series forecasting
• Network Deconvolution
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers
• Pre-training Graph Neural Networks
• A Study of BFLOAT16 for Deep Learning Training
• Mixed Precision TrainingWith 8-bit Floating Point
• Defending Against Neural Fake News
• Explainability Techniques for Graph Convolutional Networks
• RGB and LiDAR fusion based 3D Semantic Segmentation for Autonomous Driving
• Efficient 8-Bit Quantization of Transformer Neural Machine Language Translation Model
• BAYHENN: Combining Bayesian Deep Learning and Homomorphic Encryption for Secure DNN Inference
• Lattice-Based Transformer Encoder for Neural Machine Translation
• Text-based Editing of Talking-head Video
• Detecting Kissing Scenes in a Database of Hollywood Films
• The Secrets of Machine Learning: Ten Things You Wish You Had Known Earlier to be More Effective at Data Analysis
• Neural Legal Judgment Prediction in English
• GOT: An Optimal Transport framework for Graph comparison
• Can Graph Neural Networks Help Logic Reasoning?
• Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
• Explain Yourself! Leveraging Language Models for Commonsense Reasoning
• SparseSense: Human Activity Recognition from Highly Sparse Sensor Data-streams Using Set-based Neural Networks
• ActivityNet-QA: A Dataset for Understanding ComplexWeb Videos via Question Answering
• Contextual Relabelling of Detected Objects
• Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild
• Bad Global Minima Exist and SGD Can Reach Them
• Does Object RecognitionWork for Everyone?
• 3D-RelNet: Joint Object and Relational Network for 3D Prediction
• Mesh R-CNN
• Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP
• V-NAS: Neural Architecture Search for Volumetric Medical Image Segmentation
• How to make a pizza: Learning a compositional layer-based GAN model
• RankQA: Neural Question Answering with Answer Re-Ranking
• Non-Differentiable Supervised Learning with Evolution Strategies and Hybrid Methods
• Kernelized Capsule Networks
• Extracting Visual Knowledge from the Internet: Making Sense of Image Data
• Evolving Losses for Unlabeled Video Representation Learning
• Four Things Everyone Should Know to Improve Batch Normalization
• Novelty Detection via Network Saliency in Visual-based Deep Learning
• Gendered Pronoun Resolution using BERT and an extractive question answering formulation
• Redundancy-Free Computation Graphs for Graph Neural Networks
• The Generalization-Stability Tradeoff in Neural Network Pruning
• Is Attention Interpretable?
• BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization
• Improving Neural Language Modeling via Adversarial Training
• Time-Series Anomaly Detection Service at Microsoft
• Network Implosion: Effective Model Compression for ResNets via Static Layer Pruning and Retraining
• Stochastic Mirror Descent on Overparameterized Nonlinear Models: Convergence, Implicit Regularization, and Generalization
• UniDual: A Unified Model for Image and Video Understanding
• Automatically Identifying Complaints in Social Media
• 2nd Place and 2nd Place Solution to Kaggle Landmark Recognition and Retrieval Competition 2019
• Large-scale Landmark Retrieval/Recognition under a Noisy and Diverse Dataset
• BlockSwap: Fisher-guided Block Substitution for Network Compression
• NAS-FCOS: Fast Neural Architecture Search for Object Detection
• CVPR19 Tracking and Detection Challenge: How crowded can it get?
• GluonTS: Probabilistic Time Series Models in Python
• Does Learning Require Memorization? A Short Tale about a Long Tail
• Grid R-CNN Plus: Faster and Better
• Stacked Capsule Autoencoders
• MMDetection: Open MMLab Detection Toolbox and Benchmark
• XLNet: Generalized Autoregressive Pretraining for Language Understanding
• GAN-Knowledge Distillation for one-stage Object Detection
• Privacy Preserving QoE Modeling using Collaborative Learning
• Cascade R-CNN: High Quality Object Detection and Instance Segmentation
• ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation
• Modern Deep Reinforcement Learning Algorithms
• Gradient Noise Convolution (GNC): Smoothing Loss Function for Distributed Large-Batch SGD
• End-to-End 3D-PointCloud Semantic Segmentation for Autonomous Driving
• Sharing Attention Weights for Fast Transformer
• Learning Data Augmentation Strategies for Object Detection
• Fast Training of Sparse Graph Neural Networks on Dense Hardware
• Encoding Database Schemas with Relation-Aware Self-Attention for Text-to-SQL Parsers
• Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference
• Do Transformer Attention Heads Provide Transparency in Abstractive Summarization?
• Using Database Rule for Weak Supervised Text-to-SQL Generation
• From Bilingual to Multilingual Neural Machine Translation by Incremental Training
• XNect: Real-time Multi-person 3D Human Pose Estimation with a Single RGB Camera
• Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization
• Going Deeper with Point Networks
• Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization
• Representation, Exploration, and Recommendation Of Music Playlists
• Language2Pose: Natural Language Grounded Pose Forecasting
• Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation
• Lane Detection and Classification using Cascaded CNNs
• Constructing large scale biomedical knowledge bases from scratch with rapid annotation of interpretable patterns
• How we do things with words: Analyzing text as social and cultural data
• HOnnotate: A method for 3D Annotation of Hand and Objects Poses
• Time Series Anomaly Detection with Variational Autoencoders
• Real-time Claim Detection from News Articles and Retrieval of Semantically-Similar Factchecks
• Combining Q&A Pair Quality and Question Relevance Features on Community-based Question Retrieval
• SEntiMoji: An Emoji-Powered Learning Approach for Sentiment Analysis in Software Engineering
• Graph-based Knowledge Distillation by Multi-head Attention Network
• LumièreNet: Lecture Video Synthesis from Audio
• Diffprivlib: The IBM Differential Privacy Library
• Collecting Indicators of Compromise from Unstructured Text of Cybersecurity Articles using Neural-Based Sequence Labelling
• Data Encoding for Byzantine-Resilient Distributed Optimization
• Extraction and Analysis of Fictional Character Networks: A Survey
• C³ Framework: An Open-source PyTorch Code for Crowd Counting
• Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Data
• Visual Appearance Analysis of Forest Scenes for Monocular SLAM
• Multi-lingual Intent Detection and Slot Filling in a Joint BERT-based Model
• Visus: An Interactive System for Automatic Machine Learning Model Building and Curation
• Improved local search for graph edit distance
• Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions
• The What-If Tool: Interactive Probing of Machine Learning Models
• GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing
• GraphSAINT: Graph Sampling Based Inductive Learning Method
• Object Detection in Video with Spatial-temporal Context Aggregation
• Two-stream Spatiotemporal Feature for Video QA Task
• Semi-supervised Feature-Level Attribute Manipulation for Fashion Image Retrieval
• Making AI Forget You: Data Deletion in Machine Learning
• Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
• BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs
• Meet Up! A Corpus of Joint Activity Dialogues in a Visual Environment
• Privileged Features Distillation for E-Commerce Recommendations
• Large Memory Layers with Product Keys
• Time2Vec: Learning a Vector Representation of Time
• Performance Boundary Identification for the Evaluation of Automated Vehicles using Gaussian Process Classification
• Incrementalizing RASA's Open-Source Natural Language Understanding Pipeline
• Learning to learn with quantum neural networks via classical neural networks
• Adversarial Objects Against LiDAR-Based Autonomous Driving Systems
• R-Transformer: Recurrent Neural Network Enhanced Transformer
• Gated-SCNN: Gated Shape CNNs for Semantic Segmentation
• ACTNET: end-to-end learning of feature activations and multi-stream aggregation for effective instance image retrieval
• Motion Planning Networks: Bridging the Gap Between Learning-based and Classical Motion Planners
• M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
• Bringing Giant Neural Networks Down to Earth with Unlabeled Data
• ALFA: Agglomerative Late Fusion Algorithm for Object Detection
• Understanding Deep Learning Techniques for Image Segmentation
• FoodX-251: A Dataset for Fine-grained Food Classification
• Towards Generation of Visual Attention Map for Source Code
• A Divide-and-Conquer Approach Towards Understanding Deep Networks
• Automatic Repair and Type Binding of Undeclared Variables using Neural Networks
• Measuring the Transferability of Adversarial Examples
• Exploring Deep Anomaly Detection Methods Based on Capsule Net
• Sequence Level Semantics Aggregation for Video Object Detection
• Federated Reinforcement Distillation with Proxy Experience Memory
• Asking Clarifying Questions in Open-Domain Information-Seeking Conversations
• The Many AI Challenges of Hearthstone
• Improved Hybrid Layered Image Compression using Deep Learning and Traditional Codecs
• Adversarial Video Generation on Complex Datasets
• Agglomerative Attention
• Facebook FAIR's WMT19 News Translation Task Submission
• Audits as Evidence: Experiments, Ensembles, and Enforcement
• Multi-scale Graph-based Grading for Alzheimer's Disease Prediction
• Batch-Shaping for Learning Conditional Channel Gated Networks
• Real-time Hair Segmentation and Recoloring on Mobile GPUs
• Separable Convolutional LSTMs for Faster Video Segmentation
• Cascade RetinaNet: Maintaining Consistency for Single-Stage Object Detection
• AreWe Really Making Much Progress? AWorrying Analysis of Recent Neural Recommendation Approaches
• A Unified Deep Framework for Joint 3D Pose Estimation and Action Recognition from a Single RGB Camera
• How much real data do we actually need: Analyzing object detection performance using synthetic and real data
• Efficient Segmentation: Learning Downsampling Near Semantic Boundaries
• Explaining Classifiers with Causal Concept Effect (CaCE)
• On the "steerability" of generative adversarial networks
• Natural Adversarial Examples
• Fake News Detection as Natural Language Inference
• Probing Neural Network Comprehension of Natural Language Arguments
• A Survey on Explainable Artificial Intelligence (XAI): towards Medical XAI
• Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming
• Self Organizing Supply Chains for Micro-Prediction: Present and Future uses of the ROAR Protocol
• Self-Attentive Hawkes Processes
• FOSNet: An End-to-End Trainable Deep Neural Network for Scene Recognition
• AquaSight: Automatic Water Impurity Detection Utilizing Convolutional Neural Networks
• News Cover Assessment via Multi-task Learning
• Zygote: A Differentiable Programming System to Bridge Machine Learning and Scientific Computing
• Mitigating Uncertainty in Document Classification
• Clustering Activity-Travel Behavior Time Series using Topological Data Analysis
• Learning End-to-End Goal-Oriented Dialog with Maximal User Task Success and Minimal Human Agent Use
• Robustness properties of Facebook’s ResNeXt WSL models
• Gated Recurrent Neural Network Approach for Multilabel Emotion Detection in Microblogs
• Truck Traffic Monitoring with Satellite Images
• Learning Privately over Distributed Features: An ADMM Sharing Approach
• OmniNet: A unified architecture for multi-modal multi-task learning
• An Adaptive Approach for Anomaly Detector Selection and Fine-Tuning in Time Series
• Understanding Video Content: Efficient Hero Detection and Recognition for the Game "Honor of Kings"
• A Computer Vision Application for Assessing Facial Acne Severity from Selfie Images
• Deep Neural Models for Medical Concept Normalization in User-Generated Texts
• Real-Time Driver State Monitoring Using a CNN Based Spatio-Temporal Approach
• ELG: An Event Logic Graph
• Automatic Grading of Individual Knee Osteoarthritis Features in Plain Radiographs using Deep Convolutional Neural Networks
• Self-supervised Training of Proposal-based Segmentation via Background Prediction
• A Survey of Data Quality Measurement and Monitoring Tools
• OCC: A Smart Reply System for Efficient In-App Communications
• Querying Knowledge via Multi-Hop English Questions
• Multi-Task Regression-based Learning for Autonomous Unmanned Aerial Vehicle Flight Control within Unstructured Outdoor Environments
• I Stand With You: Using Emojis to Study Solidarity in Crisis Events
• GPU-Accelerated Atari Emulation for Reinforcement Learning
• Interpretable Modelling of Driving Behaviors in Interactive Driving Scenarios based on Cumulative Prospect Theory
• Cross-Domain Car Detection Using Unsupervised Image-to-Image Translation: From Day to Night
• Incremental Transformer with Deliberation Decoder for Document Grounded Conversations
• Construct Dynamic Graphs for Hand Gesture Recognition via Spatial-Temporal Attention
• Techniques for Automated Machine Learning
• DetectFusion: Detecting and Segmenting Both Known and Unknown Dynamic Objects in Real-time SLAM
• Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods
• Introduction to Neural Network based Approaches for Question Answering over Knowledge Graphs
• Visualizing the Invisible: Occluded Vehicle Segmentation and Recovery
• Multi-Class Lane Semantic Segmentation using Efficient Convolutional Networks
• MixConv: Mixed Depthwise Convolutional Kernels
• Make Skeleton-based Action Recognition Model Smaller, Faster and Better
• Effortless Deep Training for Traffic Sign Detection Using Templates and Arbitrary Natural Images
• Similarity-Preserving Knowledge Distillation
• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
• Graph Reasoning Networks for Visual Question Answering
• ChromaGAN: An Adversarial Approach for Picture Colorization
• A-MAL: Automatic Motion Assessment Learning from Properly Performed Motions in 3D Skeleton Videos
• Trading via Image Classification
• Generic Prediction Architecture Considering both Rational and Irrational Driving Behaviors
• Analyzing the Variety Loss in the Context of Probabilistic Trajectory Prediction
• From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation
• Translator2Vec: Understanding and Representing Human Post-Editors
• Counterfactual Learning from Logs for Improved Ranking of E-Commerce Products
• Semi-Supervised Tensor Factorization for Node Classification in Complex Social Networks
• SpanBERT: Improving Pre-training by Representing and Predicting Spans
• Green AI
• SDNet: Semantically Guided Depth Estimation Network
• Benchmarking TPU, GPU, and CPU Platforms for Deep Learning
• Submission to ActivityNet Challenge 2019: Task B Spatio-temporal Action Localization
• Optuna: A Next-generation Hyperparameter Optimization Framework
• DropEdge: Towards the Very Deep Graph Convolutional Networks for Node Classification
• ET-Net: A Generic Edge-aTtention Guidance Network for Medical Image Segmentation
• Cross Attention Network for Semantic Segmentation
• Weakly Supervised Recognition of Surgical Gestures
• Dynamic Input for Deep Reinforcement Learning in Autonomous Driving
• DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks
• Importance-Aware Semantic Segmentation with Efficient Pyramidal Context Network for Navigational Assistant Systems
• SlimYOLOv3: Narrower, Faster and Better for Real-Time UAV Applications
• Graph Neural Lasso for Dynamic Network Regression
• Accurate and Robust Eye Contact Detection During Everyday Mobile Device Interactions
• Semisupervised Adversarial Neural Networks for Cyber Security Transfer Learning
• Real-time Event Detection on Social Data Streams
• Non-delusional Q-learning and Value Iteration
• A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation
• Software Engineering for Machine Learning: A Case Study
• Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments
• What Makes a Video a Video: Analyzing Temporal Information in Video Understanding Models and Datasets
• Learning to ParseWireframes in Images of Man-Made Environments
• GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
• ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
• Improving Language Understanding by Generative Pre-Training
• Language Models are Unsupervised Multitask Learners
• Large-Scale Study of Curiosity-Driven Learning
• Learning to Represent Edits
• Spherical CNNs

Most Influential Data Science Research Papers:

• A General and Adaptive Robust Loss Function
• On the Origin of Deep Learning
• Neural Style Transfer: A Review
• Deep Learning: A Critical Appraisal
• Recent Advances in Recurrent Neural Networks
• Deep Learning: An Introduction for Applied Mathematicians
• Deep Learning for Sentiment Analysis: A Survey
• A New Backpropagation Algorithm without Gradient Descent
• The Matrix Calculus You Need For Deep Learning
• Averaging Weights Leads to Wider Optima and Better Generalization
• Group Normalization
• A Survey on Neural Network-Based Summarization Methods
• geomstats: a Python Package for Riemannian Geometry in Machine Learning
• Backdrop: Stochastic Backpropagation
• Relational Deep Reinforcement Learning
• An intriguing failing of convolutional neural networks and the CoordConv solution
• Backprop Evolution
• Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks
• Neural Approaches to Conversational AI: Question Answering, Task-Oriented Dialogues and Social Chatbots
• Reversible Recurrent Neural Networks

Awesome Fraud Detection Research Papers:

• Ranking Fraud Detection for Mobile Apps: A Holistic View
• Securing the Deep Fraud Detector in Large-Scale E-Commerce Platform via Adversarial Machine Learning Approach
• Graph-Based User Behavior Modeling: From Prediction to Fraud Detection
• Exposing Search and Advertisement Abuse Tactics and Infrastructure of Technical Support Scammers
• HiDDen: Hierarchical Dense Subgraph Detection with Application to Financial Fraud Detection
• REV2: Fraudulent User Prediction in Rating Platforms
• Fraud Detection with Density Estimation Trees
• AI Technologies to Defeat Identity Theft Vulnerabilities
• A Machine-Learned Proactive Moderation System for Auction Fraud Detection
• Realtime Constrained Cycle Detection in Large Dynamic Graphs
• Using Co-Visitation Networks For Detecting Large Scale Online Display Advertising Exchange Fraud
• Crowd Fraud Detection in Internet Advertising
• Large Graph Mining: Patterns, Cascades, Fraud Detection, and Algorithms
• Online Modeling of Proactive Moderation System for Auction Fraud Detection
• Using Relational Knowledge Discovery to Prevent Securities Fraud
• NetProbe: A Fast and Scalable System for Fraud Detection in Online Auction Networks
• Identifying Anomalies in Graph Streams Using Change Detection
• Detecting Fraud in Health Insurance Data: Learning to Model Incomplete Benford's Law Distributions
• Key Player Identification in Underground Forums over Attributed Heterogeneous Information Network Embedding Framework
• Fraud Detection by Generating Positive Samples for Classification from Unlabeled Data
• PD-FDS: Purchase Density based Online Credit Card Fraud Detection System
• Improving Card Fraud Detection through Suspicious Pattern Discovery
• A graph-based, semi-supervised, credit card fraud detection system
• A Pattern Discovery Approach to Retail Fraud Detection
• FRAUDAR: Bounding Graph Fraud in the Face of Camouflage
• FARE: Schema-Agnostic Anomaly Detection in Social Event Logs
• Improving Credit Card Fraud Detection with Calibrated Probabilities
• Credit Card Fraud Detection Using Meta-Learning: Issues and Initial Results
• Robust System for Identifying Procurement Fraud
• BIRDNEST: Bayesian Inference for Ratings-Fraud Detection
• Document Classification and Visualisation to Support the Investigation of Suspected Fraud
• Detecting Fraudulent Personalities in Networks of Online Auctioneers
• FrauDetector: A Graph-Mining-based Framework for Fraudulent Phone Call Detection
• Toward Scalable Learning with Non-uniform Class and Cost Distributions: A Case Study in Credit Card Fraud Detection
• Toward An Intelligent Agent for Fraud Detection — The CFE Agent
• Uncovering Download Fraud Activities in Mobile App Markets
• No Place to Hide: Catching Fraudulent Entities in Tensors
• Detection of money laundering groups using supervised learning in networks
• Call-based Fraud Detection in Mobile Communication Networks using a Hierarchical Regime-Switching Model
• Impression Allocation for Combating Fraud in E-commerce Via Deep Reinforcement Learning with Action Norm Penalty
• Online Reputation Fraud Campaign Detection in User Ratings
• Catch the Black Sheep: Unified Framework for Shilling Attack Detection Based on Fraudulent Action Propagation
• Utility-Based Fraud Detection
• Graph Analysis for Detecting Fraud, Waste, and Abuse in Healthcare Data
• Anomaly, Event, and Fraud Detection in Large Network Datasets
• Fraudulent Support Telephone Number Identification Based on Co-occurrence Information on theWeb

Machine Learning Lectures:

• Black Box Machine Learning
• Introduction to Statistical Learning Theory
• Gradient and Stochastic Gradient Descent
• Excess Risk Decomposition
• l₁ and l₂ Regularization
• Lasso, Ridge, and Elastic Net
• Loss Functions for Regression and Classification
• Lagrangian Duality and Convex Optimization
• Support Vector Machines
• Subgradient Descent
• Features
• Kernel Methods
• Performance Evaluation
• "CitySense": Probabilistic Modeling and Anomaly Detection
• Maximum Likelihood Estimation
• Conditional Probability Models
• Bayesian Methods
• Bayesian Regression
• Classification and Regression Trees
• Basic Statistics and a Bit of Bootstrap
• Bagging and Random Forests
• Gradient Boosting
• Multiclass and Introduction to Structured Prediction
• k-Means Clustering
• Gaussian Mixture Models
• EM Algorithm for Latent Variable Models
• Neural Networks
• Backpropagation and the Chain Rule
• Case Study: Churn Prediction
• Next Steps

Assignments:

---

• Homework 1: Ridge Regression, Gradient Descent, and SGD
• Homework 2: Lasso Regression
• Homework 3: SVM and Sentiment Analysis
• Homework 4: Kernel Methods
• Homework 5: Conditional Probability Models
• Homework 6: Multiclass, Trees, and Gradient Boosting
• Homework 7: Computation Graphs, Backpropagation, and Neural Networks

The 5 Algorithms for Efficient Deep Learning Inference on Small Devices:

Pruning Neural Networks:

---

• Pruning algorithms of neural networks − a comparative study
• Learning bothWeights and Connections for Efficient Neural Networks
• Pruning Neural Networks with Distribution Estimation Algorithms
• Optimal Brain Damage

Deep Compression:

---

• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding

Data Quantization:

---

• Going Deeper with Embedded FPGA Platform for Convolutional Neural Network

Low-Rank Approximation:

---

• Efficient and Accurate Approximations of Nonlinear Convolutional Networks

Trained Ternary Quantization:

---

• Trained Ternary Quantization

Neuro AI Papers:

• Neural scene representation and rendering
• Towards Biologically Plausible Deep Learning
• Compositional generalization in a deep seq2seq model by separating syntax and semantics
• Intrinsic dimension of data representations in deep neural networks
• Learning From Brains How to Regularize Machines
• Selective Brain Damage: Measuring the Disparate Impact of Model Pruning
• Deep neuroethology of a virtual rodent
• Large-Scale, High-Resolution Comparison of the Core Visual Object Recognition Behavior of Humans, Monkeys, and State-of-the-Art Deep Artificial Neural Networks
• From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction
• A unified theory for the origin of grid cells through the lens of pattern formation
• Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream
• Predictive learning extracts latent space representations from sensory observations
• Building machines that learn and think like people
• Number detectors spontaneously emerge in a deep neural network designed for visual object recognition
• Towards deep learning with segregated dendrites
• Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition

Quantum ML Papers:

• Quantum Reinforcement Learning
• Quantum Boltzmann Machine
• Quantum Perceptron Models
• Quantum Machine Learning
• Quantum gradient descent and Newton's method for constrained polynomial optimization
• Reinforcement Learning Using Quantum Boltzmann Machines
• A Survey of Quantum Learning Theory
• Quantum machine learning: a classical perspective
• Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers
• Quantum autoencoders via quantum adders with genetic algorithms
• Multiqubit and multilevel quantum reinforcement learning with quantum technologies
• Quantum Hopfield neural network
• Automated optimization of large quantum circuits with continuous parameters
• Quantum Neuron: an elementary building block for machine learning on quantum computers
• A quantum algorithm to train neural networks using low-depth circuits
• Unitary quantum perceptron as efficient universal approximator
• A generative modeling approach for benchmarking and training shallow quantum circuits
• Quantum Variational Autoencoder
• Classification with Quantum Neural Networks on Near Term Processors
• Quantum machine learning in feature Hilbert spaces
• Barren plateaus in quantum neural network training landscapes
• Towards Quantum Machine Learning with Tensor Networks
• Circuit-centric quantum classifiers
• Hierarchical quantum classifiers
• Quantum generative adversarial networks
• Quantum generative adversarial learning
• Quantum machine learning for data scientists
• Supervised learning with quantum enhanced feature spaces
• Universal discriminative quantum neural networks
• Continuous-variable quantum neural networks
• A Universal Training Algorithm for Quantum Deep Learning
• Bayesian Deep Learning on a Quantum Computer
• A quantum-inspired classical algorithm for recommendation systems
• Quantum generative adversarial learning in a superconducting quantum circuit
• Quantum algorithms and lower bounds for convex optimization
• Production of photonic universal quantum gates enhanced by machine learning
• Quantum Convolutional Neural Networks
• The Expressive Power of Parameterized Quantum Circuits
• Quantum-inspired classical algorithms for principal component analysis and supervised clustering
• An Artificial Neuron Implemented on an Actual Quantum Processor
• Quantum-inspired low-rank stochastic regression with logarithmic dependence on the dimension
• Graph Cut Segmentation Methods Revisited with a Quantum Algorithm
• q-means: A quantum algorithm for unsupervised machine learning
• Quantum Statistical Inference
• Quantum Sparse Support Vector Machines
• Efficient Learning for Deep Quantum Neural Networks
• Quantum hardness of learning shallow classical circuits
• Sublinear quantum algorithms for training linear and kernel-based classifiers
• Building quantum neural networks based on swap test
• Parameterized quantum circuits as machine learning models
• Machine Learning Phase Transitions with a Quantum Processor
• Sampling-based sublinear low-rank matrix arithmetic framework for dequantizing quantum machine learning
• Quantum Algorithms for Deep Convolutional Neural Networks
• Hybrid Quantum-Classical Convolutional Neural Networks
• Machine learning method for state preparation and gate synthesis on photonic quantum computers
• Quantum Machine Learning: What Quantum Computing Means to Data Mining

Healthcare ML Papers:

• Learning Phenotypes and Dynamic Patient Representations via RNN Regularized Collective Non-negative Tensor Factorization
• Vision Based Prediction of ICU Mobility Care Activities Using Recurrent Neural Networks
• Vision-Based Hand Hygiene Monitoring in Hospitals
• SOM-VAE: Interpretable Discrete Representation Learning on Time Series
• Near-Optimal Reinforcement Learning in Dynamic Treatment Regimes
• PGANs: Personalized Generative Adversarial Networks for ECG Synthesis to Improve Patient-Specific Deep ECG Classification
• Clinically applicable deep learning for diagnosis and referral in retinal disease
• Opportunistic Learning: Budgeted Cost-Sensitive Learning from Data Streams
• Applications of Natural Language Processing in Clinical Research and Practice
• Explanation by Progressive Exaggeration
• Emergency Department Online Patient-Caregiver Scheduling
• Adapting Neural Networks for the Estimation of Treatment Effects
• GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series
• Active Learning for Decision-Making from Imbalanced Observational Data
• Bayesian multi-domain learning for cancer subtype discovery from next-generation sequencing count data
• emrQA: A Large Corpus for Question Answering on Electronic Medical Records
• Lessons from Natural Language Inference in the Clinical Domain
• Adversarial Attacks Against Medical Deep Learning Systems
• Towards Deep Cellular Phenotyping in Placental Histology
• Fréchet ChemNet Distance: A metric for generative models for molecules in drug discovery
• Novel Exploration Techniques (NETs) for Malaria Policy Interventions
• CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
• Attend and Diagnose: Clinical Time Series Analysis using Attention Models
• Natural Language Processing for Precision Medicine
• Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks
• Dr.VAE: Drug Response Variational Autoencoder
• Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis
• A Survey on Deep Learning in Medical Image Analysis
• End-to-end training of deep probabilistic CCA for joint modeling of paired biomedical observations

Human AI Interaction Papers:

• Gamut: A Design Probe to Understand How Data Scientists Understand Machine Learning Models
• Machine Teaching: A New Paradigm for Building Machine Learning Systems
• Learning Visual Importance for Graphic Designs and Data Visualizations
• The Challenge of Crafting Intelligible Intelligence
• Scaling up analogical innovation with crowds and AI
• What Makes a Good Conversation? Challenges in Designing Truly Conversational Agents
• Exploring Factors that Influence Connected Drivers to (Not) Use or Follow Recommended Optimal Routes
• ATMSeer: Increasing Transparency and Controllability in Automated Machine Learning
• In a SilentWay: Communication Between AI and Improvising Musicians Beyond Sound
• Citizen science frontiers: Efficiency, engagement, and serendipitous discovery with human–machine systems
• On the Utility of Learning about Humans for Human-AI Coordination
• Evorus: A Crowd-powered Conversational Assistant Built to Automate Itself Over Time
• Agency plus automation: Designing artificial intelligence into interactive systems
• Updates in Human-AI Teams: Understanding and Addressing the Performance/Compatibility Trade
• BigBlueBot: Teaching Strategies for Successful Human-Agent Interactions
• Resilient Chatbots: Repair Strategy Preferences for Conversational Breakdowns
• Will You Accept an Imperfect AI? Exploring Designs for Adjusting End-user Expectations of AI Systems
• Trends and Trajectories for Explainable, Accountable and Intelligible Systems: An HCI Research Agenda
• Deep Knowledge Tracing
• The Effect of Explanations and Algorithmic Accuracy on Visual Recommender Systems of Artistic Images
• When People and Algorithms Meet: User-reported Problems in Intelligent Everyday Applications
• Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction
• Guidelines for Human-AI Interaction
• Emotional Dialogue Generation using Image-Grounded Language Models
• To Explain or not to Explain: the Effects of Personal Characteristics when Explaining Music Recommendations
• Creative Writing with a Machine in the Loop: Case Studies on Slogans and Stories
• Learning Cooperative Personalized Policies from Gaze Data
• Caring for Vincent: A Chatbot for Self-compassion
• Hands Holding Clues for Object Recognition in Teachable Machines
• Implicit Communication of Actionable Information in Human-AI teams
• SmartEye: Assisting Instant Photo Taking via Integrating User Preference with Deep View Proposal Network
• Metaphoria: An Algorithmic Companion for Metaphor Creation
• "Like Having a Really bad PA": The Gulf between User Expectation and Experience of Conversational Agents
• Cognitive Load Estimation in the Wild
• An Exploration of Speech-Based Productivity Support in the Car
• Learning Program Embeddings to Propagate Feedback on Student Code
• SearchLens: Composing and Capturing Complex User Interests for Exploratory Search
• Beyond Dyadic Interactions: Considering Chatbots as Community Members
• Tuned Models of Peer Assessment in MOOCs
• Ubicoustics: Plug-and-Play Acoustic Activity Recognition
• Designing Theory-Driven User-Centric Explainable AI
• Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference

Economics ML Papers:

• Inherent Trade-Offs in the Fair Determination of Risk Scores
• Algorithmic decision making and the cost of fairness
• Artificial Intelligence as Structural Estimation: Economic Interpretations of Deep Blue, Bonanza, and AlphaGo
• Economists (and Economics) in Tech Companies
• Estimation with Quadratic Loss
• Deep IV: A Flexible Approach for Counterfactual Prediction
• Scalable Price Targeting
• Economic Predictions with Big Data: The Illusion of Sparsity
• Artificial Intelligence, Automation, and the Economy
• Artificial Intelligence and Economic Growth
• Artificial Intelligence, Economics, and Industrial Organization
• Machine Learning and the Market for Intelligence III Notes

Text Detection Papers:

• TextBoxes: A Fast Text Detector with a Single Deep Neural Network
• Multi-Oriented Text Detection with Fully Convolutional Networks
• Robust Scene Text Recognition with Automatic Rectification
• Detecting Oriented Text in Natural Images by Linking Segments
• Scene text detection and recognition: recent advances and future trends
• Deep Direct Regression for Multi-Oriented Scene Text Detection
• Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
• Synthetic Data for Text Localisation in Natural Images

Proteins ML Papers:

• Deep Supervised and Convolutional Generative Stochastic Network for Protein Secondary Structure Prediction
• Protein Secondary Structure Prediction with Long Short Term Memory Networks
• Predicting changes in protein thermostability brought about by single- or multi-site mutations
• NeEMO: a method using residue interaction networks to improve prediction of protein stability upon mutation
• Engineering proteinase K using machine learning and synthetic genes
• Distributed Representations for Biological Sequence Analysis
• dna2vec: Consistent vector representations of variable-length k-mers
• Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity
• Variational auto-encoding of protein sequences
• Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions
• End-to-End Learning on 3D Protein Structure for Interface Prediction
• Design by adaptive sampling
• Distance-based Protein Folding Powered by Deep Learning
• Conditioning by adaptive sampling for robust design
• Learning protein sequence embeddings using information from structure
• How to Hallucinate Functional Proteins
• Batched Stochastic Bayesian Optimization via Combinatorial Constraints Design
• Leveraging binding-site structure for drug discovery with point-cloud methods
• Evaluating Protein Transfer Learning with TAPE
• Iterative Peptide Modeling With Active Learning And Meta-Learning
• Protein Sequence Design with a Learned Potential
• Repertoires of G protein-coupled receptors for Ciona-specific neuropeptides
• Generative Modeling for Protein Structures
• Machine learning-assisted directed protein evolution with combinatorial libraries
• Predicting Protein Binding Affinity With Word Embeddings and Recurrent Neural Networks
• Toward machine-guided design of proteins
• Deep Semantic Protein Representation for Annotation, Discovery, and Engineering
• Detecting Protein-Protein Interactions with a Novel Matrix-Based Protein Sequence Representation and Support Vector Machines
• Modeling the Language of Life - Deep Learning Protein Sequences
• Biological Structure and Function Emerge from Scaling Unsupervised Learning to 250 Million Protein Sequences
• UDSMProt: Universal Deep Sequence Models for Protein Classification
• DeepPrime2Sec: Deep Learning for Protein Secondary Structure Prediction from the Primary Sequences
• Machine Learning for Prioritization of Thermostabilizing Mutations for G-protein Coupled Receptors
• Improving protein function prediction with synthetic feature samples created by generative adversarial networks
• Augmenting protein network embeddings with sequence information
• DeepCLIP: Predicting the effect of mutations on protein-RNA binding with Deep Learning
• Accelerating Protein Design Using Autoregressive Generative Models
• De Novo Protein Design for Novel Folds using Guided Conditional Wasserstein Generative Adversarial Networks (gcWGAN)
• Structure-Based Function Prediction using Graph Convolutional Networks
• Expanding functional protein sequence space using generative adversarial networks
• USMPep: Universal Sequence Models for Major Histocompatibility Complex Binding Affinity Prediction
• Attention mechanism-based deep learning pan-specific model for interpretable MHC-I peptide binding prediction
• Improved protein structure prediction using predicted inter-residue orientations
• Machine Learning Predicts New Anti-CRISPR Proteins
• Transformer neural network for protein specific de novo drug generation as machine translation problem
• End-to-end multitask learning, from protein language to protein features without alignments
• Interpreting mutational effects predictions, one substitution at a time
• Improved Descriptors for the Quantitative Structure−Activity Relationship Modeling of Peptides and Proteins
• Mismatch string kernels for discriminative protein classification
• AOPs-SVM: A Sequence-Based Classifier of Antioxidant Proteins Using a Support Vector Machine
• A structural alignment kernel for protein structures
• Predicting and understanding transcription factor interactions based on sequence level determinants of combinatorial control
• Fast and accurate predictions of protein stability changes upon mutations using statistical potentials and neural networks: PoPMuSiC-2.0
• mCSM: predicting the effects of mutations in proteins using graph-based signatures
• ProFET: Feature engineering captures high-level protein functions
• DeepSite: protein-binding site predictor using 3D-convolutional neural networks
• DeepLoc: prediction of protein subcellular localization using deep learning
• DeepSol: a deep learning framework for sequence-based protein solubility prediction
• High precision protein functional site detection using 3D convolutional neural networks
• Navigating the protein fitness landscape with Gaussian processes