Data Science Online Resources
This is a list of data science learning materials organized by topics.
Table of Contents
1. Foundations
2. Data Science
3. Topics
Data Structure & Algorithms:
- Problem Solving with Algorithms and Data Structures using Python (Brad Miller and David Ranum): Book
- Grokking Algorithms (Aditya Y. Bhargava): Github
- Introduction to Algorithms by MIT: Course page with videos
Probability & Statistics:
- Stanford CS109 Introduction to Probability for Computer Scientists: Course page
- NYU 1002 Statistical and Mathematical Methods: Course page 2015
- Harvard Statistics110: Course page
- Think Bayes (Allen B. Downey): Book
- Think Stats (Allen B. Downey): Book
Python
- Python for Data Analysis (Wes McKinney):
- Learn Python the hard way: Free book
R
- R for Data Science (Hadley Wickham): Free book
Database
- Database by Stanford: Course
Others
- USF MSDS692 Data acquisition: Course page
- USF MSDS501 Computational Data Science Bootcamp: Course page
- COMPSCI 109A: Data Science 1: Introduction to Data Science: Course page
Machine Learning:
- Videos:
- Stanford Statistical Learning: Course page
- Coursera - Andrew Ng: Coursera, Youtube
- Stanford 229: Youtube, Course page
- Machine Learning Foundations: Coursera , Youtube
- Machine Learning Techniques: Youtube
- CMU 701 by Tom Mitchell: Course page
- CU W4995 Applied Machine Learning by Andreas Mueller Course page
- CU 4771 Machine Learning Course page
- Bloomberg Fondation of Machine Learning by David Rosenberg Course page
- Textbooks:
- Introduction to Statistical Learning: pdf
- Computer Age Statistical Inference: Algorithms, Evidence, and Data Science: pdf
- The Elements of Statistical Learning: pdf
- Introduction to Machine Learning with Python: github
- Comments:
Stanford Statistical Learning is a good introductory course that explains concept in simple ways and not math heavy. More advanced materials could be found in 229, 701 or ESL book.
Deep Learning
- Videos:
- Ng’s deep learning courses: Coursera
- Stanford CS230: Deep Learning: Couse page, Github
- Stanford 231n: Convolutional Neural Networks for Visual Recognition (Spring 2017): Youtube, Couse page
- Deep Learning Specialization: Youtube
- Stanford 224n: Natural Language Processing with Deep Learning (Winter 2017): Youtube, Course page
- MIT 6.S094: Deep Learning for Self-Driving Cars: Youtube, Couse page
- MIT 6.S191 Introduction to Deep Learning: Youtube
- Neural Networks for Machine Learning by Hinton: Coursera. This course is so hard for me but it covers almost everything about neural networks. Prof. Hinton is the hero.
- Keras in 30 sec: Link
- Tensorflow. Stanford CS20SI: Youtube
- Books:
- Deep learning book by Ian Goodfellow: http://www.deeplearningbook.org/. Very detailed reference book.
- ArXiv for research updates: https://arxiv.org/. I found it the mobile version of Feedly is useful to follow ArXiv. Also, try https://deeplearn.org/ or http://www.arxiv-sanity.com/top.
- Other:
- LSTM: My collection
- Comments:
Ng's courses are already good enough. Reading Part 2 of Goodfellow's book can also be helpful. Learning one kind of DL packages is important, such as Keras, TF or Pytorch. People may choose a focus, either CV or NLP. People want to have deeper understanding of DL can take Hinton's course and read Part 3 of Goodfellow's book. Fast.ai has very practical courses.
Reinforcement Learning:
- Videos:
- Udacity: Course
- UCL Course on RL by David Silver: Course page
- CS 294: Deep Reinforcement Learning by UC Berkeley, Fall 2017: Course page
- Books:
- Reinforcement Learning: An Introduction (2nd): pdf
Artificial Inteligence
I seperated AI from DL/RL here since there are some specialized AI courses. But the content of AI and DL overlappes with each other a lot.
- Courses:
- FAST.ai: Course. A practical deep learning course.
- UC Berkeley CS188 Intro to AI: Course page
- CMU 681 Artificial Intelligence by Tuomas Sandholm: Course page
- Comments:
Bayesian:
- Courses:
- Bayesian Statistics: From Concept to Data Analysis: Coursera
- Bayesian Methods for Machine Learning: Coursera
- Statistical Rethinking: Course Page (Recorded Lectures: Winter 2015, Fall 2017)
- Book:
- Bayesian Reasoning and Machine Learning: Online book
- Bayesian Data Analysis, Third Edition
- Applied Predictive Modeling
Time series:
- Courses:
- Time Series Forecasting (Udacity): Udacity
- Topics in Mathematics with Applications in Finance (MIT): Course page, Youtube
- Books:
- Time Series Analysis and Its Applications: Springer
- With LSTM:
- https://machinelearningmastery.com/time-series-prediction-lstm-recurrent-neural-networks-python-keras/
- https://machinelearningmastery.com/multivariate-time-series-forecasting-lstms-keras/
- More: https://machinelearningmastery.com/?s=Time+Series&submit=Search
Natural Language Processing:
- Videos:
- CU - W4705: Natural Language Processing: Course web
- Stanford - Basic NLP course on Coursera: Videos, Slides, AcademicTorrent
- Stanford - CS224n Natural Language Processing with Deep Learning: Course web, Videos
- CMU - Neural Nets for NLP 2017: Course web, Videos
- University of Oxford and DeepMind - Deep Learning for Natural Language Processing: 2016-2017: Course web, Videos and slides
- Sequence Models by Andrew Ng on Coursera: Coursera
- Books:
- Natural Language Processing with Python: Book
- Speech and Language Processing (3rd ed. draft): Book
- An Introduction to Information Retrieval: pdf
- Deep Learning (Some chapters or sections): Book
- A Primer on Neural Network Models for Natural Language Processing: Paper. Goldberg also published a new book this year
- Packages:
- NLTK: http://www.nltk.org/
- Stanford packages: https://nlp.stanford.edu/software/
- Comments:
The basic NLP course by Stanford is the fundamental one. SLP 3ed follows this course. After this, feel free to take one of the three NLP+DL courses. They basically cover same topics. The Stanford one have HWs available online. CMU one follows Goldberg's book. Deepmind one is much shorter.
- More:
Some other people's collections: NLP DL-NLP Speech and NLP Speech RNN
Distributed Systems:
- Courses:
- Stanford CS246: Mining Massive Dataset: Course
- Stanford CS345A: Data Mining: Course
- CU W4121 Computer Systems for Data Science: Course
- NYU Big Data: Course, Wiki
- The Ultimate Hands-On Hadoop: Udemy
- Spark and Python for Big Data with PySpark: Udemy
- Docker Mastery: Udemy
- Books:
Cryptography
- Courses:
- Stanford CS255: Introduction to Cryptography: Course
- Stanford CS 355: Topics in Cryptography: Course
- Books:
A Graduate Course in Applied Cryptography: book
Analytics:
- Lean Analytics: Amazon
- Data Science for Business: Amazon
- Data Smart: Amazon
- Storytelling with Data: Amazon
- How to Win a Data Science Competition: Coursera
- How to finish a Data Challenge: Kaggle EDA kernels
- Mining Massive Datasets by Stanford: Free book, Course
- Recommender System by UMN: Coursera
Communications:
- Lists with Solutions:
- 111 Data Science Interview Questions & Detailed Answers: Link
- 40 Interview Questions asked at Startups in Machine Learning / Data Science Link
- 100 Data Science Interview Questions and Answers (General) for 2017 Link
- 21 Must-Know Data Science Interview Questions and Answers Link
- 45 Questions to test a data scientist on basics of Deep Learning (along with solution) Link
- 30 Questions to test a data scientist on Natural Language Processing Link
- Questions on Stackoverflow: Link
- Compare two models: My collection
- Without Solutions:
- Over 100 Data Science Interview Questions Link
- 20 questions to detect fake data scientists Link
- Question on Glassdoor: link
Quant:
- Courses:
- Financial Markets with Robert Shiller (Yale): Youtube, Coursera
- Topics in Mathematics with Applications in Finance (MIT): Youtube, Course page
- Other:
- A Collection of Dice Problems: pdf