CSEP 573 - Applications of Artificial Intelligence

University of Washington Department of Computer Science & Engineering

CSEP 573 - Applications of Artificial Intelligence - Winter 2016
Thurs 6:30-9:20 in JHN 111

Instructor: Luke Zettlemoyer (lsz at cs)
Office hours: After class TA: Fereshteh Sadeghi (fsadeghi at cs)
Office hours: Thurs 5:30-6:30 in CSE614

Schedule [subject to change!]

Week	Dates	Topics & Lecture Notes	Readings
1	Jan 7	Introduction; Search	R&N, Ch. 1,2 (optional); R&N Ch.3.1-3.4
2	Jan 14	Heuristic Search; Adversarial Search	R&N, Ch.3.5-3.7; 5.1-5.4
3	Jan 21	Expectimax; Markov Decision Processes (MDPs)	R&N, Ch.5.5-5.7;17.1-17.3
4	Jan 28	MDPs (cont); Reinforcement Learning (RL)	R&N, Ch.21.1- 21.5
5	Feb 4	RL (cont); Uncertainty	R&N, Ch.13
6	Feb 11	Hidden Markov Models (HMMs)	R&N, Ch.15.1
7	Feb 18	HMM (cont.); Bayesian Networks (BNs);	R&N, Ch.15.1-15.3
8	Feb 25	BN (cont.); Inference in Bayesian Networks	R&N, Ch.14.1-14.5
9	Mar 3	Machine Learning
10	Mar 10	Neural Networks, Vision Overview, Summary

Textbook

Stuart Russell & Peter Norvig, Artificial Intelligence: A Modern Approach, Prentice-Hall, Third Edition (2009) [R&N].

Programming Projects

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: Jan 24 by 11:45pm)
Project 2: MultiAgent Pacman (Due: Feb 7 by 11:45pm)
Project 3: MDPs & RL (Due: Feb 28 by 11:45pm)
Project 4: Ghostbusters (Inference and Filtering) (Due: Mar 13 at 11:45pm)

Exam

Midterm Exam (Due: Feb 15 at 11:45pm)
Final Exam (Due: Mar 20 at 11:45pm)

Communication

Course Administration and Policies

Your grade will be as follows:
- 55% programming assignments
- 20% take home midterm
- 20% take home final exam
- 5% class participation.
Assignments policy
- Assignments will 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.
- Each student has four penalty-free late day for the whole quarter. All other late submissions will be penalized 20% of the maximum grade per day.

Department of Computer Science & Engineering
University of Washington
Box 352350
Seattle, WA 98195-2350
(206) 543-1695 voice, (206) 543-2969 FAX