- The most recommended is Andrew NG's ML course on Coursera
- edX Machine Learning by Columbia
- Learning From Data by CalTech on edX
- University of Washington's ML specialization on Coursera
- Udacity courses, some could be easier for beginners
- Carnegie Melon University Machine Learning Course YouTube playlist
- Understanding Machine Learning: From Theory to Algorithms, Shai Shalev-Shwartz and Shai Ben-David
- Elements of Statistical Learning
- Pattern Recognition and Machine Learning (or PRML) [$], Christopher Bishop
- Pattern Classification [$], R. Duda, P.E. Hart and D.G Stork
- Machine Learning [$], Tom Mitchell
- Machine Learning: a Probabilistic Perspective [$], Kevin Patrick Murphy
- Information Theory, Inference, and Learning Algorithms
- Computer-age Statistical Inference [$], Bradley Efron and Trevor Hastie
- An Introduction to Statistical Learning [$], Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani
- The Elements of Statistical Learning [$], Trevor Hastie, Robert Tibshirani and Jerome Friedman, Advanced difficulty
- Machine Learning Yearning, Andrew Ng
- The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World [$], Pedro Domingo
- Perceptrons: An Introduction to Computational Geometry, Expanded Edition [$]
- Parallel Models of Associative Memory [$]
- Mining of Massive Datasets [$], Jure Leskovec, Anand Rajaraman and Jeffrey David Ullman
- Data Science Handbook [$], Carl Shan, William Chen, Henry Wang and Max Song
- David Silver's videos
- John Schulman's lectures
- By Georgia Tech on Udacity
- AI: Reinforcement Learning in Python
- AI: Deep Reinforcement Learning in Python
Based on Awesome DL Papers
- Human-level control through deep reinforcement learning, V. Mnih et al., 2015
- Mastering the game of Go with deep neural networks and tree search, D. Silver et al., 2016
- Playing Atari with deep reinforcement learning, V. Mnih et al., 2013
- End-to-end training of deep visuomotor policies, S. Levine et al., 2016
- Asynchronous methods for deep reinforcement learning, V. Mnih et al., 2016
- Continuous control with deep reinforcement learning, T. Lillicrap et al., 2015
- Deep learning for detecting robotic grasps, I. Lenz et al., 2015
- Deep Reinforcement Learning with Double Q-Learning, H. Hasselt et al., 2016
- Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection, S. Levine et al., 2016
- The first neural network model: McCullotch Pitts Model; A logical calculus of the ideas immanent in nervous activity
- First Networks which could learn: Perceptron; The perceptron: A probabilistic model for information storage and organization in the brain
- The holy algorithm of DL: Back Propagation; Learning representations by back-propagating errors