Schedule

Announcements

Lecture videos are available from the Canvas site (in the menu on the left) by selecting Echo 360.

To use jupyter notebooks on our CS department machines, you must add this line to your .bashrc file:

export PATH=/usr/local/anaconda/bin:$PATH

This is a tentative schedule of CS440 topics for Fall, 2018. This will be updated during the summer and as the fall semester continues.

Week	Topic	Material	Reading	Assignments
Week 1: Aug 20 - Aug 24	What is AI? Promises and fears. Python review. Problem-Solving Agents.	01 Introduction to AI 02 Introduction to Python	Chapters 1, 2, 3.1 of Russell and Norvig. AI, People, and Society, by Eric Horvitz. Automated Ethics, by Tom Chatfield. The Great A.I. Awakening, by Gideon Lewis-Krause, NYT, Dec 14, 2016. "Fundamental Existential Threat": Lawmakers Warned of the Risks of Killer Robots, by Julia Conley Section 1 of Scipy Lecture Notes
Week 2: Aug 27 - Aug 31	Problem-solving search and how to measure performance. Iterative deepening and other uninformed search methods.	03 Problem-Solving Agents 04 Measuring Search Performance 05 Iterative Deepening and Other Uninformed Search Methods 06 Python Implementation of Iterative Deepening	Sections 3.1 - 3.4 of Russell and Norvig

Week	Topic	Material	Reading	Assignments
Week 3: Sept 4 - Sept 7 No class on the Sept 3 (University Holiday) and Sept 5(instructor traveling). Sept 7 is optional. GTAs will answer assignment questions.	Informed search. A* search. Python classes, sorting, numpy arrays.		Rest of Chapter 3	A1 Uninformed Search due Friday, Sept. 7, 10:00 PM. Submit your notebook in Canvas. Here are good solutions from your classmates
Week 4: Sept 10 - Sept 14	Informed search. A* search. Python classes, sorting, numpy arrays. A* optimality, admissible heuristics, effective branching factor. Local search and optimization.	07 Informed Search 08 Python Classes 09 Heuristic Functions 10 Local Search	Chapter 4	A2 Iterative-Deepening Search due Friday, Sept. 14, 10:00 PM. Submit your notebook in Canvas. Here are good solutions from your classmates
Week 5: Sept 17 - Sept 21	Adversarial search. Minimax. Alpha-beta pruning. Stochastic games.	11 Adversarial Search	Chapter 5
Week 6: Sept 24 - Sept 28	Negamax, with pruning. Introduction to Reinforcement Learning.	12 Negamax 13 Modern Game Playing 14 Introduction to Reinforcement Learning	Chapter 21 Reinforcement Learning: An Introduction	A3 A*, IDS, and Effective Branching Factor due Wednesday, Sept. 26, 10:00 PM. Submit your notebook in Canvas.

Week	Topic	Material	Reading	Assignments
Week 7: Oct 1 - Oct 5	Reinforcement Learning for Two-Player Games.	14 Introduction to Reinforcement Learning 15 Reinforcement Learning for Two-Player Games	Chapter 21 Reinforcement Learning: An Introduction
Week 8: Oct 8 - Oct 12	Introduction to Neural Networks	16 Introduction to Neural Networks 17 More Introduction to Neural Networks	Sections 18.6 and 18.7
Week 9: Oct 15 - Oct 19	More Neural Networks. Autoencoders.	17 More Introduction to Neural Networks 22 Autoencoder Neural Networks
Week 10: Oct 22 - Oct 26	Introduction to Classification. Bayes Rule. Generative versus Discriminative. Linear Logistic Regression.	18 Introduction to Classification		A4 Reinforcement Learning Solution to Towers of Hanoi due Monday, Oct. 22, 10:00 PM. Submit your notebook in Canvas.

Week	Topic	Material	Reading	Assignments
Week 11: Oct 29 - Nov 2	Classification with Neural Networks. Reinforcement Learning with Neural Networks.	19 Classification with Linear Logistic Regression 20 Classification with Nonlinear Logistic Regression Using Neural Networks 21 Reinforcement Learning with a Neural Network as the Q Function
Week 12: Nov 5 - Nov 9	Introduction to Pytorch. Constraint satisfaction. Min-conflicts.	23 Introduction to Pytorch 24 Constraint Satisfaction Problems 25 Min-Conflicts in Python with Examples	Chapter 6 A new iterated local search algorithm for solving broadcast scheduling problems in packet radio networks	A5 Neural Networks due Monday, Nov. 5, 10:00 PM. Project Proposal due Friday, November 9th, at 10:00 PM.
Week 13: Nov 12 - Nov 16	Natural language understanding and translation.	26 Natural Language 27 Word Embeddings	Word2Vec and FastText Word Embedding with Gensim
Nov 19 - Nov 23	Fall Recess
Week 14: Nov 26 - Nov 30	Faster Reinforcement Learning	Slides for Faster Reinforcement Learning After Pretraining	Faster Reinforcement Learning After Pretraining Deep Networks to Predict State Dynamics by Anderson, Lee and Elliott	A6 Min-Conflicts due Wednesday, Nov. 28, 10:00 PM.

Week	Topic	Material	Reading	Assignments
Week 15: Dec 3 - Dec 7	Voluntary in-class project presentations.	Dec 3: Tom Cavey: Image Classification and Object Detection of Things Around CSU Jason Stock: Classification of Data from the Sloan Digital Sky Survey Marylou Nash: Physical Routing on ICs or PCBs with A* Dec 5: Jake Walker: Legal, Ethical, and Security Concerns for Autonomous Driving Technologies Andy Dolan: Using Machine Learning Methods to Classify BGP Messages Miles Wood: Using Q-Learning to Learn to Play Chad, a Chess Variant Apoorv Pandey: Using Q-Learning to Learn to Play 2×2 Dots and Boxes Dec 7: Markus Dabell: Classification of Handwritten Digits from the MNIST Dataset Sajeeb Roy Chowdhury: Searching for Optimal Schreier Trees in the Field of Combinatorics Mike Hamilton: The Amazon AWS DeepRacer Platform for Reinforcement Learning Experimentation
Final Exam Week: Dec 10 - Dec 14				Final Project notebook is due Tuesday, Dec 11th, 10:00 pm. Here is an notebook explaining what is expected for your final report.