CSE 573 - Introduction to Artificial Intelligence

CSE 573 - Introduction to Artificial Intelligence - Winter 2020
Wed, Fri 1:30-2:50pm in ECE 045

Instructor: Hanna Hajishirzi
Office hours:
Mon 4-5 pm, Allen 654

TA: Aida Amini
Office hours:
Thu 1-2 pm, Allen 220

TA: Andrey Ryabtsev
Office hours:
Wed 12-1 pm, Allen 220

Schedule [subject to change!]

Week	Dates	Topics & Lecture Notes	Readings	Assignments
1	Jan 8, 10	Introduction; Search	R&N, Ch. 1,2 (optional); R&N 3.1-3.4	PS0 No Due Date
2	Jan 15, 17	Informed Search [Annotated]	R&N 3.5-3.7, 4; Search visualization tool
3	Jan 22, 24	Adversarial Search; Expectimax [Annotated]	R&N 5.1-5.5	PS1 Due: Jan 24
4	Jan 29, 31	Markov Decision Processes (MDPs) [Annotated]; Solving MDPs	R&N 17.1-17.3; 15-15.3
5	Feb 5, 7	Reinforcement Learning (RL) [Annotated]	R&N 21.1-21.5	PS2 Due: Feb 5
6	Feb 12, 14	Reinforcement LearningII (RL-II) [Annotated]; Uncertainty [Annotated]	R&N 15.1; 15.3 and 15.5	HW1 Due: Feb 12
7	Feb 19, 21	Bayesian Networks [Annotated]; Hidden Markov Models (HMMs) [Annotated]	R&N 13; 14 thru 14.5	Project Proposal Due Feb 19 PS3 Due: Feb 21
8	Feb 26, 28	Hidden Markov Models; [Annotated] HMM Filtering	R&N 14.1-14.3	Paper Report Due Feb 26
9	March 4, 6	Inference in Bayesian Networks [Annotated];Naive Bayes	R&N 14.4-14.5	PS4 Due: March 6
10	March 11, 13	Application; Project poster Session	R&N 6; 18.1-18.2; 20.1-20.2	HW2 Due: March 13; Project posters: March 16(3pm)

Required: Stuart Russell & Peter Norvig, Artificial Intelligence: A Modern Approach, Prentice-Hall, Third Edition (2009) [R&N].
Useful: Mausam, Andrey Kolobov. Planning with Markov Decision Processes: An AI Perspective Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan and Claypool Publishers. June 2012. (free online version if accessed from UW) [M&K]
Useful: Richard Sutton & Andrew Barto, Reinforcement Learning: An Introduction, MIT Press. (limited chapters; freely available online) [S&B]

This quarter, we will do The Pac-Man Projects. Please complete the versions listed below, as they differ in places from the originals.

Project 0: Python Tutorial (Not Graded)
Project 1: Search in Pacman (Due Friday 1/24 at 11:59 PM)
Project 2: MultiAgent Pacman (Due Wednesday 2/5 at 11:59 PM)
Project 3: MDPs & RL (Due Friday 2/21 at 11:59 PM)
Project 4: Ghostbusters (Inference and Filtering) (Due Friday 3/6 at 11:59 PM)

Available on Canvas.

Please follow these instructions regarding your final project:

Projects can be done in a group of one to two students.
We encourage you to work on research projects that are close to your research areas. As a reference, we also provide a list of potential projects. Your final project can also be a re-implementation of one of the recent papers from AI/ML/NLP/Computer vision conferences.
Project Proposal (20 points, Due: Feb. 19th) The project proposal is a 1-page summary of the project topic, motivation, definition, dataset, and resources. It should also include the milestones, detailed experiment plan, and the timeline to complete each milestone.
Project Presentation (40 points, Due: March 16th, 3pm): UPDATED: We will have the poster presentation remotely. Each team should make a presentation in form of poster or slides, record a presentation over it and upload it for grading. More instructions can be find here
Project Report (40 points, Due: March 19th): Your write up should be about 4 pages maximum (not including references) in Camera-ready NIPS format . You may have unlimited appendices for clarifications, however, your main content should appear in the 4-page limit.

Your grade will be 5% class participation, 5% paper reports, 30% programming assignments, 30% homeworks, and 30% project.
Assignments should be done individually unless otherwise specified. You may discuss the subject matter with other students in the class, but all final answers must be your own work. You are expected to maintain the utmost level of academic integrity in the course.
Late Policy (***EXCEPT FINAL PROJECT***): Each student has Six penalty-free late day for the whole quarter, other than that any late submission will be penalized at a penalty of 20% of the maximum grade per day.
Penalty-free late days are not applicable to Final Project. The maximum late days that can be used per assignment is four.