Resources

Starting Places

• AITopics.org
• Educational Advances in AI (EAAI)
• Model AI Assignments

General

• Texts:
  • Stuart Russell, Peter Norvig. Artificial Intelligence: a modern approach

Machine Learning

• Texts:
  • Christopher Bishop. Pattern Recognition and Machine Learning
  • Kevin Murphy. Machine Learning: A Probabilistic Perspective
  • David Barber. Probabilistic Reasoning and Machine Learning (Barber's free PDF version)
  • Tom Mitchell. Machine Learning
  • Ethem Alpaydin. Introduction to Machine Learning
  • Statistical Learning:
    • Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning
    • Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. An Introduction to Statistical Learning with Applications in R (RStudio software for labs)
  • Reinforcement Learning:
    • Richard Sutton and Andrew Barto. Reinforcement Learning: an introduction
    • Csaba Szepesvári. Algorithms for Reinforcement Learning
    • Marco Wiering and Martijn van Otterlo. Reinforcement Learning: State-of-the-Art
  • KDNuggets "10 Free Must-Read Books for Machine Learning and Data Science"
• Online resources:
  • Andrew Ng's free online Coursera Machine Learning course
  • UC Irvine Machine Learning Repository
  • Kaggle datasets
  • RStudio software for labs
  • Weka Java-based Data Mining software and Ian Witten and Eibe Frank. Data Mining: Practical Machine Learning Tools and Techniques
  • Model AI Assignments
  • Berkeley student crash course on ML
• Recommendations:
  • Quora "How do I learn machine learning?" answers
  • Joseph Misiti's Machine Learning book recommendations

Neural Network Learning

• Textbooks
  • Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
  • Michael Nielson's Neural Networks and Deep Learning online book.
• Websites
  • Waikit Lau and Arthur Chan's Artificial Intelligence and Deep Learning (AIDL) Facebook group and FAQ
  • A Guide to Deep Learning by YerevaNN Labs
  • Piotr Migdał's Learning Deep Learning with Keras
  • a16z team's reference links
  • Stanford's CS 231n Convolutional Networks course website
  • various Wikipedia pages concerning artificial neural networks
  • TensorFlow Playground
  • Why Momentum Really Works
  • Xiu-Shen Wei's Must Know Tips/Tricks in Deep Neural Networks
  • Medium.com guide: Understanding Activation Functions
  • John Schulman's Deep RL Hacks (summarized by William Falcon)
  • Michael Dietz's Understand Deep Residual Networks
• Online Courses
  • Andrew Ng's Machine Learning course and Coursera Deep Learning specialization
  • Geoffrey Hinton's Neural Networks for Machine Learning course
  • Hugo Larochelle's graduate-level online Neural Network course
  • David Venturi's list of Deep Learning online courses
  • Arthur Chan's top 5
• Software
  • TensorFlow and Keras
  • Microsoft Cognitive Toolkit (CNTK)
  • Theano
  • Torch and PyTorch)
  • Caffe
  • MXNet
  • DeepLearning4J
  • Comparison of deep learning software and April 2017 popularity metrics
• Hardware
  • Tim Dettmers' GPU comparison study
  • Ved's d4datascience blog entry on setting up a GPU-based deep learning machine

Hidden Markov Models

• Video Introductions
  • Daphne Koller's 12-minute video "Template Models: Hidden Markov Models - Stanford University"
  • Nando de Freitas' 52-minute UBC lecture "undergraduate machine learning 9: Hidden Markov models - HMM"
• Texts and Articles
  • Russell and Norvig, Artificial Intelligence: a modern approach, 3rd ed, sections 15.3, 20.3.3.
  • Speech and Language Processing, 3rd ed, Chapter 9 by Daniel Jurafsky and James H. Martin
  • Lawrence Rabiner tutorial "A tutorial on hidden Markov models and selected applications in speech recognition"
  • Christopher Bishop's "Pattern Recognition and Machine Learning", Section 13.2
  • StackExchange thread "Resources for learning Markov chain and hidden Markov models"
• Other Resources
  • Udacity's `"Intro to Artificial Intelligence" course by Peter Norvig and Sebastian Thrun
  • Udacity's "Artificial Intelligence - Probabalistic Models"
  • Coursera's Ge Gao lecture on HMMs
  • Jason Eisner's spreadsheet for teaching the forward-backward algorithm and his paper on using it for teaching
  • Quora question "What are some good resources for learning about Hidden Markov Models?"
• Model AI Assignments
  • Sravana Reddy's "Implementing a Hidden Markov Model Toolkit"
  • John DeNero and Dan Klein's "The Pac-Man Projects" Project #4: Ghostbusters

Click-Through Rate (CTR) Prediction

• Kaggle CTR Prediction Competitions:
  • Criteo
  • Avazu
  • Avito
  • Outbrain
• XGBoost - Extreme Gradient Tree Boosting
  • XGBoost: A Scalable Tree Boosting System
• libffm - library for Field-aware Factorization Machines (FFMs)
  • Field-aware factorization machines for CTR prediction
  • Slides on winning approach to Criteo CTR Prediction competition