Machine Learning Resources - uclaacmai/ai-wiki GitHub Wiki

If you find a resource that isn't on here, please add it!

ACM's Post on Getting Started in Machine Learning: https://medium.com/techatucla/getting-started-in-machine-learning-c68bdd739c44

Recommended Background before you begin

• Programming Proficiency (CS 32 level)
• Knowledge of Python
• Basics of calculus and statistics (chain rule, derivatives of summations, independence, Bayes Theorem)

Introduction to Machine Learning

• Python Machine Learning: https://sebastianraschka.com/pdf/books/pymle/errata_1st.pdf (most advised, very practical and every algorithm is implemented from scratch)
• Coursera Course that started it all: https://www.coursera.org/learn/machine-learning
• Pattern Recognition and Machine Learning (very in-depth): http://www.springer.com/us/book/9780387310732
• Slides from UCLA CS 260/CS 188/CS M146: http://web.cs.ucla.edu/~ameet/teaching/winter17/cs260/

Math/Theory heavy

• Review of probability theory: http://cs229.stanford.edu/section/cs229-prob.pdf
• Linear Algebra Review: http://cs229.stanford.edu/section/cs229-linalg.pdf
• Convex Optimization: http://cs229.stanford.edu/section/cs229-cvxopt.pdf
• Machine Learning, a Probabalistic Perspective (grad-level treatment): https://www.amazon.com/Machine-Learning-Probabilistic-Perspective-Computation/dp/0262018020
• Elements of Statistical Learning: https://statweb.stanford.edu/~tibs/ElemStatLearn/

Deep Learning Focused

• http://www.deeplearningbook.org/
• Neural Networks, Convnets, and more: http://cs231n.stanford.edu/
• Deep Learning for NLP: https://cs224d.stanford.edu/

Scalable & Distributed Machine Learning

Reinforcement Learning

Essential Libraries & Other Practical Things

Cool Datasets

Key Papers (reading the Deep Learning book before these would be a good idea)

• The first paper on "AI": http://www-formal.stanford.edu/jmc/history/dartmouth/dartmouth.html
• Decision Trees (most commonly used algorithm in industry): http://hunch.net/~coms-4771/quinlan.pdf
• SVMs (very commonly used): http://www.svms.org/training/BOGV92.pdf
• Fast algorithm for deep learning (started all of the current research in deep learning): https://www.cs.toronto.edu/~hinton/absps/fastnc.pdf
• Convolutional Networks (state of the art in image recognition): https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks
• Recurrent Neural Networks/LSTM (state of the art in NLP): https://static.googleusercontent.com/media/research.google.com/en//pubs/archive/43905.pdf
• Generative Adversarial Networks: https://arxiv.org/abs/1406.2661

Other AI