Machine Learning courses/books/etc

Books

An Introduction to Statistical Learning by Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani

• covers statistical learning without too much exposure to math (originally course was designed for the MBA students).
• good explanation of the bias-variance dilemma.
• good explanation of linear and logistic regression with examples and comparison with kNN, LDA, QDA (linear/quadratic discriminant analysis).

Deep Learning by Ian Goodfellow, Yoshua Bengio, Aaron Courville

• just the best book about deep learning at that moment.

Reinforcement Learning: An Introduction 2nd edition by Richard Sutton and Andrew Barto

• bible of the reinforcement learning, a bit outdated but super good.

ML Courses

Stanford CS224n: Natural Language Processing with Deep Learning with video.

Stanford CS 20SI: Tensorflow for Deep Learning Research

Stanford CS231n: Convolutional Neural Networks for Visual Recognition with video

Berkeley CS 294: Deep Reinforcement Learning, Fall 2017

RL Course by David Silver - DeepMind

Course on Information Theory, Pattern Recognition, and Neural Networks

Some math courses that help to understand ML

MIT 18.06: Linear Algebra with video

• just well designed course about linear algebra (matrix factorizations, SVD, PCA, etc).

MIT 6.041 / 6.431: Probabilistic Systems Analysis and Applied Probability with video

• really good introduction into probability.

Real Analysis course at Harvey Mudd College (follows baby Rudin) youtube

Magazines/Articles

Journal of Machine Learning Research

• highly respected scholar magazine with free access

arxiv.org with Machine Learning tag

• archive of pre-prints, you can checkout papers of such giants like Yoshua Bengio, Andrew Y. Ng, Yann LeCun, Bernhard Schölkopf, etc.

Articles of DeepMind

• The best recommendation is a cite from wiki - "The company made headlines in 2016 after its AlphaGo program beat a human professional Go player for the first time"

Math Courses

Linear Algebra Done Wrong

CS053ta: Coding the Matrix, Fall 2014 - Brown (http://codingthematrix.com/)

STAT 505 - Applied Multivariate Statistical Analysis

POP 507 / ECO 509 / WWS 509 - Generalized Linear Statistical

Theory and Use of the EM Algorithm

10.34: Numerical Methods Applied to Chemical Engineering - MIT

CS

CS 224: Advanced Algorithms - Harvard

6.006: Introduction to Algorithms - MIT

6.046J/18.410J: Design and Analysis of Algorithms - MIT

6.849: Geometric Folding Algorithms: Linkages, Origami, Polyhedra - MIT

6.890: Algorithmic Lower Bounds: Fun with Hardness Proofs - MIT

6.851: Advanced Data Structures - MIT

Epilogue

The goal of this list is to provide some resources/books about Machine Learning that I found useful for me (if you know something interesting, drop a comment - I will add).