This is an old revision of the document!

Schedule

Announcements

Links to live MS Teams events:

Recordings of lecture and office hour videos are available from the Home page of our Canvas site.

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, 2020. This will be updated during the summer and as the fall semester continues.

Week	Topic	Material	Reading	Assignments
Week 1: Aug 24 - Aug 28	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. Section 1 of Scipy Lecture Notes AI, People, and Society, by Eric Horvitz. Automated Ethics, by Tom Chatfield. The Great A.I. Awakening, by Gideon Lewis-Krause

Week	Topic	Material	Reading	Assignments
Week 2: Aug 31 - Sept 4	Problem-solving search and how to measure performance. Iterative deepening and other uninformed search methods.	03 Problem-Solving Agents 04 Measuring Search Performance	Sections 3.1 - 3.4 of Russell and Norvig
Week 3: Sept 7 - Sept 11	Informed search. A* search. Python classes, sorting, numpy arrays.		Rest of Chapter 3	A1 Uninformed Search due Tuesday, Sept. 8, 10:00 PM. Submit your notebook in Canvas.
Week 4: Sept 14 - Sept 18	A* optimality, admissible heuristics, effective branching factor. Local search and optimization.		Chapter 4
Week 5: Sept 21 - Sept 25	Adversarial search. Minimax. Alpha-beta pruning. Stochastic games.		Chapter 5
Week 6: Sept 28 - Oct 2	Negamax, with pruning. Introduction to Reinforcement Learning.		Chapter 21 Reinforcement Learning: An Introduction

Week	Topic	Material	Reading	Assignments
Week 7: Oct 5 - Oct 9	Reinforcement Learning for Two-Player Games.		Chapter 21 Reinforcement Learning: An Introduction
Week 8: Oct 12 - Oct 16	Introduction to Neural Networks		Sections 18.6 and 18.7
Week 9: Oct 19 - Oct 23	More Neural Networks. Autoencoders.
Week 10: Oct 26 - Oct 30	Introduction to Classification. Bayes Rule. Generative versus Discriminative. Linear Logistic Regression.

Week	Topic	Reading
Week 11: Nov 2 - Nov 6	Classification with Neural Networks. Reinforcement Learning with Neural Networks.
Week 12: Nov 9 - Nov 13	Introduction to Pytorch. Constraint satisfaction. Min-conflicts.	Chapter 6 A new iterated local search algorithm for solving broadcast scheduling problems in packet radio networks
Week 13: Nov 16 - Nov 20	Natural language understanding and translation.	Word2Vec and FastText Word Embedding with Gensim
Nov 23 - Nov 27	Fall Recess!

Week	Topic	Reading
Week 14: Nov 30 - Dec 4	Faster Reinforcement Learning	Faster Reinforcement Learning After Pretraining Deep Networks to Predict State Dynamics by Anderson, Lee and Elliott
Week 15: Dec 7 - Dec 11
Final Exam Week: Dec 14 - Dec 18