AI Practitioner

"One way of learning AI"

Links to helpful resources

Self Learning
Introduction
Data Analysis
Machine Learning
Deep Learning
Backers
Sponsors
Acknowledgment

Self Learning

Self Learning Resources

Books

Python Machine Learning by Sebastian Raschka and Vahid Mirjalili.

Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow, 2nd Edition. Online version of the book can be found @GitHub

Hands-On Machine Learning with Scikit-Learn and TensorFlow

Concepts, Tools, and Techniques to Build Intelligent Systems

Deep Learning with Python by Francois Chollet (the founder of Keras language)

Deep Learning with Python introduces the field of deep learning using the Python language and the powerful Keras library. Written by Keras creator and Google AI researcher François Chollet, this book builds your understanding through intuitive explanations and practical examples.

Deep Learning Book by Ian Goodfellow, Aaron Courville and Yoshua Bengio
Reinforcement Learning, Second Edition by Richard S. Sutton and Andrew G. Barto.

This second edition focuses on core online learning algorithms, with the more mathematical material set off in shaded boxes. Part I covers as much of reinforcement learning as possible without going beyond the tabular case for which exact solutions can be found. Many algorithms presented in this part are new to the second edition, including UCB, Expected Sarsa, and Double Learning. Part II extends these ideas to function approximation, with new sections on such topics as artificial neural networks and the Fourier basis, and offers expanded treatment of off-policy learning and policy-gradient methods. Part III has new chapters on reinforcement learning's relationships to psychology and neuroscience, as well as an updated case-studies chapter including AlphaGo and AlphaGo Zero, Atari game playing, and IBM Watson's wagering strategy. The final chapter discusses the future societal impacts of reinforcement learning.

Papers

Deep Learning Papers Reading Roadmap

If you are a newcomer to the Deep Learning area, the first question you may have is "Which paper should I start reading from?" Above is a reading roadmap of Deep Learning papers!

arXiv.org

Open access to 1,489,618 e-prints in Physics, Mathematics, Computer Science, Quantitative Biology, Quantitative Finance, Statistics, Electrical Engineering and Systems Science, and Economics. Maintain by Cornell University

Arxiv Sanity Preserver

Built in spare time by @karpathy to accelerate research.

Machine Learning & Data Analysis

University of Berkeley CS 188 | Introduction to Artificial Intelligence | Fall 2018

This course will introduce the basic ideas and techniques underlying the design of intelligent computer systems. A specific emphasis will be on the statistical and decision-theoretic modeling paradigm.

Coursera Machine Learning

This course provides a broad introduction to machine learning, datamining, and statistical pattern recognition. Topics include: (i) Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks). (ii) Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning). (iii) Best practices in machine learning (bias/variance theory; innovation process in machine learning and AI).

Teach you the fundamental building blocks and the theory necessary to be a responsible machine learning practitioner in your own community.

Deep Learning

Free courses from fast.ai

Stanford University Computer Vision (cs231n) (2016)
Stanford University Natural Language Processing (cs224n)
Deep Reinforcement Learning @ UCL by Google Deep Mind team.

Mathematics

fast.ai | Computational Linear Algebra for Coders

Another course offered by fast.ai

3Blue 1Brown

Animated math. centers around presenting math with a visuals-first approach.

Forums

Blogging

Towards Data Science

Competitions

Kaggle

Opportunities

Self Learn People Profiles/Projects

60 Day Deep Reinforcement Learning Challenge by Andrea Lonza.
1 Year ML Journey an Andrea Lonza.

Introduction

View repository and user information, control your notifications and even manage your issues and pull requests. Built with React Native, GitPoint is one of the most feature-rich unofficial GitHub clients that is 100% free.

Available for both iOS and Android.

Features

A few of the things you can do with GitPoint:

View user activity feed
Communicate on your issue and pull request conversations
Close or lock issues
Apply labels and assignees
Review and merge pull requests
Create new issues
Star, watch and fork repositories
Control your unread and participating notifications
Easily search for any user or repository

Feedback

Feel free to send us feedback on Twitter or file an issue. Feature requests are always welcome. If you wish to contribute, please take a quick look at the guidelines!

If there's anything you'd like to chat about, please feel free to join our Gitter chat!

Contributors

This project follows the all-contributors specification and is brought to you by these awesome contributors.

Build Process

Follow the React Native Guide for getting started building a project with native code. A Mac is required if you wish to develop for iOS.
Clone or download the repo
yarn to install dependencies
yarn run link to link react-native dependencies
yarn start:ios to start the packager and run the app in the iOS simulator (yarn start:ios:logger will boot the application with redux-logger)
yarn start:android to start the packager and run the app in the the Android device/emulator (yarn start:android:logger will boot the application with redux-logger)

Please take a look at the contributing guidelines for a detailed process on how to build your application as well as troubleshooting information.

Development Keys: The CLIENT_ID and CLIENT_SECRET in api/index.js are for development purposes and do not represent the actual application keys. Feel free to use them or use a new set of keys by creating an OAuth application of your own. Set the "Authorization callback URL" to gitpoint://welcome.