CSE 473 - Introduction to Artificial Intelligence, Autumn 2023

Paul G. Allen School of Computer Science & Engineering

CSE 473 - Introduction to Artificial Intelligence - Autumn 2023
Mon/Wed/Fri, 2:30-3:20 PM in CSE2 G20

Staff email : cse473-au23-staff@cs.washington.edu

Instructor: Hanna Hajishirzi
Office hours: Tue, 9AM-9:45AM (bi-weekly, starting Oct 3)
Location: Zoom

TA: Akari Asai Office hours: Wed, 9:30AM-10:30AM Location: CSE 678	TA: Yizhong Wang Office hours: Wed, 4PM-5PM Location (hybrid): CSE 678 and Zoom	TA: Skyler Hallinan Office hours: Fri, 10:30AM-11:30AM Location: Zoom	TA: Michael Lee Office hours: Thu, 11AM-12PM Location: CSE2 153	TA: Benlin Liu Office hours: Fri, 3:30PM-4:30PM Location: CSE2 274	TA: Wisdom Ikezogwo Office hours: Tue, 11AM-12PM Location: Zoom
TA: William Howard-Snyder Office hours: Thu, 1PM-2PM Location: CSE1 220	TA: Stefan Todoran Office hours: Mon, 11:30AM-12:30PM Location: CSE2 131	TA: Khushi Khandelwal Office hours: Mon, 12PM-1PM Location: CSE1 5th Floor breakout	TA: Kevin Farhat Office hours: Thu, 2:30-3:30 Location: CSE2 152	TA: Rohan Gupta Office hours: Tue, 12:00PM-1:00PM Location: Zoom

Schedule [subject to change!]

Week	Dates	Topics & Slides	Lecture Notes	Readings	Programming Assignments	Written Assignments	Quizzes
1	Sep 27, 29	Introduction; Search	Search Notes	R&N 1-2; 3.1-3.4 Search Visualization Tool	PS0 No Due Date
2	Oct 2, 4, 6	Search; Informed Search;	Informed Search Notes	R&N 3.5-3.7, 4; 5.1-5.4
3	Oct 9, 11, 13	Informed Search; Adversarial Search;		R&N 5.5
4	Oct 16, 18, 20	Adversarial Search; Expectimax;	Adversarial Search/Expectimax Notes	R&N 17	PS1 Due: Oct 20	HW1 Due: Oct 16	Quiz 1: Oct 20
5	Oct 23, 25, 27	Markov Decision Processes (MDPs)		R&N 22.1-22.5
6	Oct 30, Nov 1, 3	Markov Decision Processes (MDPs)	MDP Notes	R&N 22; 12, 13.1-13.4	PS2 Due: Nov 3
7	Nov 6, 8, 10	Reinforcement Learning	RL Notes	R&N 19, 19.6-19.9
8	Nov 13, 15, 17	Reinforcement Learning II; Uncertainty		R&N 21
9	Nov 20, 22, 24	Bayes Nets; Markov Models;	Uncertainty Notes	R&N 14.1-14.3
10	Nov 27, 29, Dec 1	Hidden Markov Models (HMMs);	HMMs Notes	R&N 14.2			Quiz 2: Nov 29
11	Dec 4, 6, 8	Applications; Machine Learning; Language Modeling

Textbooks

Optional: 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]

Programming Assignments

This quarter, we will do The Pac-Man Projects. Please complete the versions listed below, as they differ in places from the originals. All work will be turned in electronically. Assignments will be due at 11:59 PM on the specified date.

Project 0: Python Tutorial (Not Graded)
Project 1: Search in Pacman (Due: Oct 20 at 11:59 PM)
Project 2: MultiAgent Pacman (Due: Nov 3 at 11:59 PM)
Project 3: MDPs & RL (Due: Nov 22 at 11:59 PM)
Project 4: HMM & Particle Filtering (Due: Dec 14 at 11:59 PM; cannot use late days)

Written Assignments

We estimate there will be 4 written homework assignments throughout the quarter. All work will be turned in electronically. Assignments will be due at 11:59 PM on the specified date.

Homework 1 (PDF): Due Oct 16 at 11:59 PM
Homework 2: Due Oct 30 at 11:59 PM
Homework 3: Due Nov 15 at 11:59 PM
Homework 4: Due Dec 8 at 11:59 PM

In-class Quizzes

We will have two in-class quizzes throughout the quarter which will be half an hour each; these are designed to be knowledge-checks.

Quiz 1: Oct 20
Quiz 2: Nov 29

Discussion Board

Please use Ed for course related questions.

Course Administration and Policies

Your grade is determined by: 45% programming assignment, 45% written homework, and 10% in-class quizzes.
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: 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; the maximum late days that can be used per assignment is four.

Inclusion

We welcome students from all backgrounds and adhere to the Allen School’s Inclusiveness Statement. If anything related to the course makes you feel unwelcome in any way, let the instructor know.

Accommodation

We are eager to provide necessary accommodations.

For disability accommodations, please see the UW resources.

For religious accommodations, please see the UW resources.

We recognize that our students come from varied backgrounds and can have widely-varying circumstances. If you have any unforeseen or extenuating circumstance that arise during the course, please do not hesitate to contact the instructor to discuss your situation. The sooner we are made aware, the more easily these situations can be resolved. Extenuating circumstances may include:

Work-school balance
Familial responsibilities
Unexpected travel
... or anything else beyond your control which may negatively impact your performance in the class