Artificial Intelligence CS 5300/CS 6300 Spring 2010 Schedule: Tue/Thr 12:25-1:45pm Location: WEB 2230 Instructor: Hal Daume III: Office Hours: MEB 3126; Wednesday 1:15-2:45, or by appointment Mailing list: cs5300@list.eng.utah.edu -- PLEASE subscribe (but don't post)! teach-cs5300@list.eng.utah.edu -- PLEASE post (by don't subscribe)! RSS feed TAs: Bo Wang (office hours: Friday 10-11am, MEB 3115) Matthew Ord (office hours: Monday 2-3pm, CADE 224)

4 Feb: Please fill out the early course survey!

Coursework will consist of two kinds of assignments. Programming projects will be in Python. Programming projects may be done in teams of two or three and will be graded on a point basis. Written homeworks will be in the form of mini-assignments given most weeks. These mini-assignments will be very short (one or two exam-style questions) and will be graded in on a complete / incomplete basis. You should be prepared to do regular work each week to keep up with the material and the assignments.

Prerequisites: CS 3500 (prior programming experience is expected; although we don't expect that you know Python, we do expect you to be able to pick it up rapidly); CS 2100 (facility with basic concepts of propositional logic and probability are expected). NOTE: This course has substantial elements of both programming and mathematics, because these elements are central to modern AI. You should be prepared to review basic probability on your own if it is not fresh in your head.

Expectations: I expect you to work hard, but will help you as much as possible to understand the material. However, I do expect you to read the book. I've tried to keep the readings as short as is reasonable. I expect you to do this ahead of time and come to class prepared: homeworks due on before class on day X will include topics we will discuss in class on day X. We will talk about solution in class if people have questions.

• Homework assignments (22%)
• Programming projects (35%)
• Midterm exam (18%)
• Final exam (25%)

Lateness: Homework assignments may not be turned in late. You may turn one programming project in up to two days late with no penalty. Other projects may be turned up up to two days late, but once they're one minute late, you lose 50% of your points (i.e., if you would have gotten 90%, you will instead get 45%).

Please use our online handin sofware. Homeworks are NOT accepted by email. You can view the current grades (indexed by the ID you give us on HW00; "++" means "bonus").

We will post solutions to homeworks and projects quickly after the due dates. We will also email you your scores once grading has been completed. If you handed something in and do not get a score for an assignment, you have a one week moritorium on complaints.

Here are some example midterms. The one from Spring 2009 here was WAY too long (see solution). Here are also some from previous semesters at Berkeley. Note that the format won't be exactly the same, but the style of questions for ours will be similar. Fall 2008, Fall 2007, Spring 2006, Fall 2006.

Artificial Intelligence: A Modern Approach (Third Edition)
by Stuart Russell and Peter Norvig. Prentice Hall, 2009.

Be sure you have the Third Edition. It is BLUE, not GREEN or BURGUNDY): the other editions are not sufficient (sorry!).

We will also occasionally have readings from:

Reinforcement Learning: An Introduction
by Richard S. Sutton and Andrew G. Barto. MIT Press, 1998.

This book is available online.

Date	Topics	Readings	Due	Notes
12 Jan	Introduction to AI	opt: RN 1.1,2	-
Agents
14 Jan	Agents Depth and breadth first search	3.1,3.3,3.4 opt: RN 3.2	HW00
19 Jan	Agents II A* Search and Heuristics	3.5-3.6	P0
21 Jan	Constraint Satisfaction Search and iterative algorithms	RN 6-6.3 opt: RN 4.1	HW01
26 Jan	Constraint Satisfaction II Tree-structured CSPs and more search	RN 6.4-6.5 opt: Tree_decomposition	-	-
28 Jan	Game Playing Minimax search	RN 5-5.3 opt: RN 5.5-5.6 slides	HW02
2 Feb	Utility Consistency and risk	16-16.3 opt: RN 16.4 help: q1 q2 q3 l1 l2 l3	P1
Reinforcement Learning
4 Feb	Markov Decision Processes Value iteration	SB 3-4	HW03
9 Feb	Markov Decision Processes II Policy iteration and TD-learning	RN 17.1-3, SB 6.1,6.2	-
11 Feb	Reinforcement Learning Exporation/exploitation, Q-learning	SB 6.5	HW04
16 Feb	Catch-up	SB 8.1,8.2	P2
18 Feb	Reinforcement Learning II Policy methods and IRL	-	HW05
23 Feb	Robot motion	RN 25.4-25.6	-
25 Feb	MIDTERM (solution) S09 exam (which was way too long)	-	-	-
Reasoning Under Uncertainty
2 Mar	Probability Everything you need to know!	RN 13-13.5 opt: RN 13.6	-
4 Mar	Bayes' Nets Graphical models and conditional independence	RN 14-14.3 opt: RN 14.4	HW06
9 Mar	Bayes' Nets II Causality	-	-
11 Mar	Class Cancelled	-	P3,HW07	-
16 Mar	Bayes' Nets III Inference by enumeration, variable elimination	RN 14.4	-
18 Mar	Bayes' Nets IV Markov Chain Sampling	RN 14.5	HW08
30 Mar	Decision Diagrams Value of information, Markov chains	RN 16.5-16.6	-
1 Apr	HMMs Monitoring and robot localization	RN 15-15.3	HW09
6 Apr	HMMs II Particle filtering and resampling	RN 15.5	-	-
8 Apr	HMMs III Linear space models: Kalman filtering	RN 15.4 opt: Kalman_filter	P4,HW10
Applications
13 Apr	Speech Viterbi and acousting modeling	RN 23.5	-
15 Apr	Natural Language Processing Machine Translation	RN 23.4	-
20 Apr	Machine learning Classification	RN 24.3-24.4 opt: RN 24-24.2	-
22 Apr	POMDPs Agents under uncertainty	Dummies, Sec 3-6	HW12
27 Apr	Last Day Party Philosophy of AI and exam discussion	-	-
30 Apr	FINAL EXAM, 10:30 am - 12:30 pm Spring 2009 Final Spring 2010 Final Solution	-	-	-
07 May	End of exam period	-	P5,contest	-

• Uniform Cost Search
• Greedy Best First Search
• Admissable Heuristics
• A-Star Search #1 [pdf]
• A-Star Search #2 [ppt]
• Game Trees
• Alpha Beta Pruning
• Markov Decision Processes
• Value Iteration [ppt]
• Q-Learning #1
• Q-Learning #2
• Probability
• Markov Chains
• Inference by Enumeration
• Likelihood Weighting
• Variable Elimination
• Kalman Filters
• Speech Recognition

If you want more practice, see the recommended book exercises.

• HW00: Student Survey [TeX]
• HW01: Search and CSPs [TeX] (solution)
• HW02: Game Playing [TeX] (solution)
• HW03: Utility and MDPs [TeX] (solution)
• HW04: Reinforcement Learning [TeX] (solution)
• HW05: Reinforcement Learning II [TeX] (solution)
• HW06: Probability [TeX] (solution)
• HW07: Bayesian Networks [TeX]
• HW08: Bayesian Networks II [TeX]
• HW09: HMMs [TeX]
• HW10: HMMs II [TeX] (solution)
• HW11 : Cancelled!
• HW12: Machine Learning [TeX] (solution)

• P0: Python Tutorial
• P1: Pacman Search (solution)
• P2: Pacman Multiplayer (solution)
• P3: Reinforcement Learning
• P4: Static Ghostbusters (solution)
• P5: Dynamic Ghostbusters

In fact, since our class is running in parallel with the Berkeley course, the Pacman Competition will be a cross-university competition! (Okay, it's not as compelling as U vs. Y or Berkeley vs. Stanford, but at least the colors are right: we're red and they're blue!)

ADA: The University of Utah conforms to all standards of the Americans with Disabilities Act (ADA). If you wish to qualify for exemptions under this act, notify the Center for Disabled Students Services, 160 Union.

College guidelines: Document concerning adding, dropping, etc. here.