Cmput 455 Resources

About Resources
General Background
- Background on Algorithms
- Online AI Courses
Specific Background
- Appendix A: Python Bootcamp
Lecture 1 - The game of Go and Computer Go
Lecture 2 - Basic Data Structures and Algorithms for Computer Go
Lecture 3 - Problem solving and Decision-making
Lecture 4 - Formalizing Decision-making and Games
Lecture 7 - Introduction to Search and Heuristic Search
Lecture 8 - Minimax and Alphabeta Part 1
Lecture 17 - Introduction to Machine Learning for Heuristic Search

About Resources

Links to external resources are provided as-is, for additional reading, watching and listening, without any guarantees that the material will stay accessible, be relevant for your needs, or match the contents of our course.
Resources include introductory books, articles, online courses, blog posts, demos and video clips.

General Background

Background on Algorithms

Algorithms by Dasgupta, Papadimitriou and Vazirani. McGraw-Hill Higher Education, 2008. ISBN 978-0-07-352340-8.
http://mitpress.mit.edu/books/introduction-algorithms CLRS - a classic large textbook covering many standard algorithms.
UofA library guide for Computing Science
Safari books online, large selection of textbooks, including many related to this course. Access through UofA library subscription.

Online AI Courses

Patrick Winston, MIT, Fall 2010 AI lecture videos

Appendix A: Python bootcamp

These notes cover some required background knowledge. I expect many of the students to know much of this material, so it is provided to enable you to fill in any "gaps".

Some of the activities and all of the assignments will require this knowledge.

External links:

Programming for Everybody (Getting Started with Python) and Python Data Structures. Coursera courses by Charles Severance, University of Michigan.
PEP 8 -- Style Guide for Python Code, and pep8 - Python style guide checker

Lecture 1 - The game of Go and Computer Go

Wikipedia Go page
American Go Association resources
Canadian Go Association
Go Quest for iPhone, iPad and Android by Yasushi Tanase. Play quick games on small board against other humans and a few bots.
Video Tutorial
- Video Tutorial for the Game of Go - Part I, Overview by Goshawk Heron
- Video Tutorial for the Game of Go - Part 2, Playing by Goshawk Heron
- Video Tutorial for the Game of Go - Part 3a, Terminology by Goshawk Heron
- Video Tutorial for the Game of Go - Part 3b, Concepts by Goshawk Heron

Lecture 2

Go UI's, tools

Gomill - Tools and Go library written in Python by Matthew Woodcraft

Open Source Computer Go Programs

Cmput 455 Go programs. This series of simple Go programs is used to illustrate many of the concepts taught in this course.
Ray, Rayon, Rayn
Darkforest by Yuandong Tian and Yan Zhu of Facebook. DCNN and MCTS. Darkforest on github. Written in C and Lua.
Fuego – C++ libraries and Go playing program. One of the strongest open source MCTS programs before DCNN. Developed mainly at Alberta. Currently not under active development, but still used for research.
Pachi - one of the strongest open source MCTS programs before DCNN. Written in C. Pachi on github.
Michi Minimalistic Go MCTS Engine, by pachi author Petr Baudis. Only about 500 lines of Python, MCTS and large patterns. No DCNN.
Nochi Minimalistic AlphaGo Zero reimplementation, by pachi author Petr Baudis. Based on Michi.
Oakfoam, and Detlef Schmicker's version with DCNN. Written in C++.
KataGo One of the currently (as of 2020) strongest open source Go programs. Trained using the AlphaZero algorithm on 28 GPUs, with a long list of Go specific and general enhancements to speed up the training process and improve playing strength. Paper describing most of the main improvements can be read here.

Lecture 3

Decision-Making Case Studies

How UPS Trucks Saved Millions of Dollars By Eliminating Left Turns

Chances and Risks of Algorithms

Mona Chalabi, Weapons of Math Destruction: Cathy O'Neil adds up the damage of algorithms. Guardian interview with Cathy O'Neil. Quote: "models are opinions embedded in mathematics".
Lee Rainie and Janna Anderson, Pew Research Center. Code-Dependent: Pros and Cons of the Algorithm Age

Lecture 4

Human Decision-Making

Read more about Herb Simon: wikipedia
Kahneman and Tversky: How two trailblazing psychologists turned the world of decision science upside down. Michael Lewis, Vanity Fair, November 2016.

Lecture 7 - Search and heuristic search

Blind Search - Depth-first Search, Breadth-first search, etc.

Heuristic Search

Heuristic search extra slides (best-first search, Dijkstra, branch and bound, dealing with complex problems - abstraction, divide and conquer)
redblobgames.com very detailed A* introduction.
redblobgames.com very detailed A* implementation.
Shaul Markovitch algorithm animations: BFS, A*, GBFS, alphabeta and more.

Lecture 8

Solving Go

Exploring Positional Linear Go. Noah Weninger and Ryan Hayward, Advances in Computers Games 2017.

Lecture 17

Machine Learning

A Few Useful Things to Know about Machine Learning. Pedro Domingos, Communications of the ACM 55 (10), October 2012, Pages 78-87.
Martin Zinkevich (Google, former UofA) Rules of Machine Learning: Best Practices for ML Engineering .

Lecture 18

Lecture 19

Andrew Trask, A Neural Network in 11 lines of Python (Part 1) and A Neural Network in 13 lines of Python (Part 2 - Gradient Descent)

Lecture 20

DCNN for Move Prediction in Go

Play against the Clark-Storkey Network. DCNN only, no search.

Neural Networks and Deep Learning

Andrej Karpathy's blog, Hacker's guide to Neural Networks.
Krizhevsky, Sutskever and Hinton. ImageNet Classification with Deep Convolutional Neural Networks. The original DCNN paper.
Stanford CS course CS231n: Convolutional Neural Networks for Visual Recognition.
Deep Learning with TensorFlow. Just one example of dozens of such books coming on the market now. Available through UofA library (see above).
Russ Salakhutdinov Deep Learning talk
CBC online article with interview of Geoff Hinton, sparse huge neural networks
Zeiler and Fergus (2013), Visualizing and Understanding Convolutional Networks.

Residual Networks

Kaiming He, Xiangyu Zhang, Shaoqing Ren and Jian Sun. Deep Residual Learning for Image Recognition. The paper introducing Residual Networks, "resnets".
Michael Dietz, Understand Deep Residual Networks — a simple, modular learning framework that has redefined state-of-the-art. Blog post with sample implementation in Python3/Keras.

Lecture 21 Reinforcement Learning

Artificial Intelligence’s Next Big Step: Reinforcement Learning.Mary Branscombe, The New Stack. Article about RL, not very technical.
David Silver - Lecture 1: Introduction to Reinforcement Learning. First of a ten lecture class by Dave Silver on RL.
Marc Bellemare, ML Tutorial: Modern Reinforcement Learning and Video Games. Introduction to RL and playing atari games with RL.

Lecture 22

AlphaGo

DeepMind AlphaGo page
Exploring the Frontiers of Knowledge. Demis Hassabis about AI (and Alphago) and it's future
AlphaGo and the Future of Computer Games: A Conversation at the University of Alberta Video with local UofA experts.
Is AlphaGo Really Such a Big Deal? Article by Michael Nielsen in Quanta Magazine.

AlphaGo Matches

2015 vs Fan Hui
2016 vs Lee Sedol: Alpha Go movie
January 2017, fast games on internet against almost all of the top 20 human professionals. 60 wins no losses for AlphaGo. Humans Mourn Loss After Google Is Unmasked as China’s Go MasterArticle in WSJ (needs registration or subscription)
2017 vs Ke Jie
2017 self play games https://deepmind.com/research/alphago/alphago-vs-alphago-self-play-games/ Article by Carl Johan Ragnarsson on medium.com https://medium.com/@carljohanragnarsson/lessons-from-alphago-storytelling-bias-and-program-management-7c65f9d91305