CSE 511A: Introduction to Artificial Intelligence – Fall 2016

Instructor: Professor Roman Garnett
TAs: Gustavo Malkomes (luizgustavo), Dina Elreedy (dinaelreedy), Shali Jiang (shalijiang), Hongjing Zhang (hongjing)
Time/Location: Tuesday/Thursday 4–5:30pm, Louderman Hall 458
Office hours (Garnett): Wednesdays 2:30–4pm, Jolley Hall 504
Office hours (TAs): Mondays 4–6pm, Jolley Hall 517
Office hours (TAs): Fridays 1–3pm, Jolley Hall 517
syllabus
Piazza message board Please ask all questions on Piazza!


Description

The discipline of artificial intelligence (AI) is concerned with building systems that think and act like humans or rationally on some absolute scale. This course is an introduction to the field, with special emphasis on sound modern methods. The topics include knowledge representation, problem solving via search, game playing, logical and probabilistic reasoning, planning, machine learning (decision trees, neural nets, reinforcement learning, and genetic algorithms) and machine vision. Programming exercises will concretize the key methods. The course targets graduate students and advanced undergraduates. Evaluation is based on programming assignments, a midterm exam, and a final exam.

Prerequisites

If you are unsure about any of these, please speak with the instructor.

Assignments

Please post all questions to Piazza!

You can find autograder information here.

Project 0 is due Tuesday, 6 September, 2016. Project 0 leaderboard
Project 1 is due Tuesday, 20 September, 2016. Project 1 leaderboard
Project 2 is due Tuesday, 11 October, 2016. Project 2 leaderboard
Project 3 is due Tuesday, 1 November, 2016. Project 3 leaderboard
Project 4 is due Tuesday, 22 November, 2016. Project 4 leaderboard
The contest is due Tuesday, 20 December, 2015 (last day of class no extension!). Contest leaderboard

Lectures

Lecture 1: Introduction

Tuesday, 30 August 2016
lecture slides
lecture videos

Additional Resources:

Lecture 2: Uninformed Search

Thursday, 1 September 2016
lecture slides
lecture videos

Additional Resources:

Lectures 3–4: Informed Search

Tuesday/Thursday 6/8 September 2016
lecture slides
lecture videos

Additional Resources:

Lecture 5: Constraint Satisfaction Problems

Tuesday, 13 September 2016
lecture slides
lecture videos

Additional Resources:

Lecture 6: Constraint Satisfaction Problems II

Thursday, 15 September 2016
lecture slides
lecture videos

Additional Resources:

Lecture 7: Adversarial Search

Tuesday, 20 September 2016
lecture slides
lecture videos

Additional Resources:

Lecture 8: Expectimax

Thursday, 22 September 2016
lecture slides
lecture videos

Additional Resources:

Lecture 9: Markov Decision Processes I

Tuesday, 27 September 2016
lecture slides

Additional Resources:

Lecture 10: Markov Decision Processes II

Thursday, 29 September 2016
lecture slides

Additional Resources:

Lecture 11: Reinforcement Learning I

Tuesday, 4 October 2016
lecture slides
lecture videos

Additional Resources:

Lecture 12: Reinforcement Learning II

Thursday, 6 October 2016
lecture slides
lecture videos

Additional Resources:

Lecture 13: Probability

Thursday, 20 October 2016
lecture slides

Additional Resources:

Lecture 14: Markov Models

Tuesday, 25 October 2016
lecture slides
lecture videos

Additional Resources:

Lecture 15: Hidden Markov Models

Thursday, 27 October 2016
lecture slides

Additional Resources:

Lecture 16: Particle Filters / Applications of HMMs

Tuesday, 1 November 2016
lecture slides

Additional Resources:

Lecture 17: Bayes Nets I

Thursday, 3 November 2016
lecture slides

Additional Resources:

Lecture 18: Bayes Nets II

Tuesday, 15 November 2016
lecture slides

Additional Resources:

Lecture 19: Decision Diagrams/VPI

Thursday, 17 November 2016
lecture slides
lecture videos

Additional Resources:

Lecture 20: Artificial Neural Networks

Tuesday, 22 November 2016
slides

Additional Resources:

Resources

This course is based on the CS 188 course at UC Berkeley. You may find lectures, slides, and more there.

Books

The required book for this course is Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig. Either the second or third edition is fine. This is a classic textbook and highly recommended!

Another good reference for reinforcement learning is Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto. The book is available online here.

Python help