CSE 511A: Introduction to Artificial Intelligence – Spring 2020

Instructor: Professor Roman Garnett
TAs: Nicole Wang, Zhihan Li, Jiahao Li, Tiancheng He
Time/Location: Monday/Wednesday 2:30–4pm, Steinberg 105
Office hours (Garnett): Wednesdays after class, Steinberg 105
Office hours (TA): Mondays 4–5:30pm, Jolley Hall 408
Office hours (TA): Tuesdays 4–6pm, Jolley Hall 408
Office hours (TA): Fridays 12–4pm, Jolley Hall 408
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 Monday, 20 January, 2020. Project 0 leaderboard
Project 1 is due Monday, 10 Feburary, 2020. Project 1 leaderboard
Project 2 is due Wednesday, 26 February, 2020. Project 2 leaderboard
Project 3 is due Monday, 30 March, 2020. Project 3 leaderboard
Project 4 is due Monday, 20 April, 2020. Project 4 leaderboard
The contest is due Tuesday, 5 May, 2020 (no extension!!). Contest leaderboard

Lectures

Lecture 1: Introduction

Monday, 13 January 2020
lecture slides
lecture videos

Additional Resources:

Lecture 2: Uninformed Search

Wednesday, 15 January 2020
lecture slides
lecture videos

Additional Resources:

Lectures 3: Informed Search

Wednesday, 22 January 2020
lecture slides
lecture videos

Additional Resources:

Lecture 4: Constraint Satisfaction Problems

Monday, 27 January 2020
lecture slides
lecture videos

Additional Resources:

Lecture 5: Constraint Satisfaction Problems II

Wednesday, 29 January 2020
lecture slides
lecture videos

Additional Resources:

Lecture 6: Adversarial Search

Monday, 3 Feburary 2020
lecture slides
lecture videos

Additional Resources:

Lecture 7: Expectimax

Wednesday, 5 February 2020
lecture slides
lecture videos

Additional Resources:

Lecture 8: Markov Decision Processes I

Monday, 10 February 2020
lecture slides

Additional Resources:

Lecture 9: Markov Decision Processes II

Monday, 17 February 2020
lecture slides

Additional Resources:

Lecture 10: Reinforcement Learning I

Wednesday, 19 February 2020
lecture slides
lecture videos

Additional Resources:

Lecture 11: Reinforcement Learning II

Monday, 24 February 2020
lecture slides
lecture videos

Additional Resources:

Lecture 12: Probability

Wednesday, 26 February 2020
lecture slides

Additional Resources:

Lecture 13: Markov Models

Monday, 23 March 2020
lecture slides
lecture videos

Additional Resources:

Lecture 14: Hidden Markov Models

Wednesday, 25 March 2020
lecture slides
lecture videos

Additional Resources:

Lecture 15: Particle Filters / Applications of HMMs

Monday, 30 March 2020
lecture slides
lecture videos
CIG 2014 slides
CIG 2014 paper

Additional Resources:

Lecture 16: Bayes Nets I

Wednesday, 1 April 2020
lecture slides

Additional Resources:

Lecture 17: Bayes Nets II

Monday, 8 April 2020
lecture slides

Additional Resources:

Lecture 19: Decision Diagrams/VPI

Wednesday, 15 April 2020
lecture slides
lecture videos

Additional Resources:

Lecture 20: Naive Bayes

Monday, 20 April 2020
lecture slides

Additional Resources:

Lecture 21: Artificial Neural Networks

Wednesday, 22 April 2020
slides
slides 2

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