Artificial Intelligence

CSE 441/541
Artificial Intelligence
Fall Quarter 2006

Time : Tuesdays and Thursdays, 12:00-1:50pm
Location: Shattuck Hall (SH), Room 145.

Instructor: Melanie Mitchell, FAB 120-24, (503) 725-2412,
Office hours: Tuesdays and Thursdays, 2:00-3:00pm, or by appointment.

TA: Dan Brown, FAB 115-D.
Office hours: Wednesdays, 2:00-4:00pm.

Course Website: :

Prerequisites: CS 202, 311.

Textbook: S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach , Second Edition , Prentice Hall. ISBN: 0-13-790395-2.

Reserve Readings: TBA

Assignments: There will be several short written assignments designed to solidify what is learned in class. In addition, each student will read one assigned paper or set of papers in the AI literature and give a 10- to 20-minute presentation of that paper in class.

Finally, each student will participate in a small team to carry out an AI programming project that utilizes at least two of the techniques we learn about in class. The team will also write a 10-20 page paper on this work, including a discussion of one or two related papers in the literature. During the last week of class, each team will give a 15-20 minute presentation of their project.

Exams: There will be one midterm and one final exam.

Grading: Homework: 20%; Project, paper, and in-class presentations: 40%; Midterm: 20%; Final exam: 20%.

Academic integrity: Students will be responsible for following the PSU Student Conduct Code, and in particular, the policy concerning academic honesty.

Collaboration policy: Homework: Students may discuss the general concepts and principles behind an assignment with other students. In fact, you are encouraged to do this whenever possible, because it is often a valuable way to reinforce ideas, and to learn new perspectives. However, in doing assignments, each student is expected to develop, write up, and hand in an individual solution and, in doing so, develop a sufficient understanding of the problem and solution so as to be able to explain it adequately to the instructor. Under no circumstances should a student copy or consult the solution of another student, or copy a solution from any other source, including the Internet. Team projects: Again, students are free to discuss general concepts and issues of the projects with anyone. However, all programming and writing of the paper should be done exclusively by each the team.

Students with disabilities: If you are a student with a disability in need of academic accommodations, you should register with Disability Services for Students and notify the instructor immediately to arrange for support services.

Syllabus (subject to change):



Reading and Homework

Tuesday Sept. 26

Introduction to AI

Philosophical foundations of AI

Slides from today's class.


John Searle, Minds, Brains, and Programs.

Optional reading:

Textbook, Chapters 1, 26.

Alan Turing, Computing Machinery and Intelligence.

Homework assigned: Homework 1 ("Commentary on Searle paper"). Due Thursday Sept. 28.

Thursday Sept. 28

Introduction to AI

Philosophical foundations of AI, continued.

Slides from today's class.

Student presentations: Commentaries on Searle's article

Tim Hamilton presentation

David Florey presentation

Homework due: Homework 1 ("Commentary on Searle paper").

Tuesday Oct. 3

Agents, robots, and search

Student presentations: Commentaries on Searle's article, continued

Jesse Joe Bernardo

Reading: Textbook, Chapters 2-3,

Homework assigned: Homework 2, due Tuesday Oct. 10.

Thursday Oct. 5

Agents, robots, and search continued.

Here is the paper I talked about today on ARA*:
Likhachev, M., Gordon, G., and Thrun, S., ARA*: Anytime A* with provable bounds on sub-optimality.

Student presentations:

Davy: Braitenberg, Vehicles (1-8)

Dain: Brooks, Intelligence without representation (Here are Dain's presentation slides.)

Wren: Breazeal & Scassellati, Challenges in building robots that imitate people

All project teams should be formed. One-paragrpah project proposals due Thursday Oct. 12.

Tuesday, Oct. 10

Search and game playing (Guest lecture: Bart Massey)

Bart's slides

Reading: Textbook, Chapters 4,6

Homework due: Homework 2.

Homework assigned: Homework 3 (Search and Game-Playing), due Tuesday October 17.

Thursday, Oct. 12

Search and game playing, continued

Student presentations:

Sean: (Sean's slides )
Buro, M.
The evolution of strong Othello programs
Buro, M. Takeshi Murakami vs. Logistello
D. E. Moriarty and R. Miikkulainen, Discovering complex Othello strategies through evolutionary neural networks

Jessica: (Jessica's slides)
Schaeffer, J. et al., A world championship caliber checkers program
Schaeffer, J. et al., Chinook: The world man-machine checkers champion

Campbell, M. et al., Deep Blue
Stork, D. G., Hal, Deep Blue, and Kasparov

Project proposals.

Project proposals due.

Tuesday, Oct. 17

Neural networks

Lecture slides

Reading: Textbook, Section 20.5, Chapter 21

Homework due: Homework 3.

Homework assigned: Homework 4 (Reinforcement Learning; Biologically Inspired AI), due Tuesday Oct. 24.

Thursday, Oct. 19

Reinforcement learning and biologically inspired AI

Reinforcement learning slides

Genetic algorithms slides

Student presentations:

Joel Hoffman: (Joel's slides)
G. Tesauro, Temporal difference learning and TD-Gammon

Trevor Elliot:
S. Baluja, Evolution of an artificial neural network based autonomous land vehicle controller

Reading: Chapter 1 of M. Mitchell, An Introduction to Genetic Algorithms (handed out in class).

Tuesday, Oct. 24

Biologically inspired AI and learning, continued

Slides on schemas

Review for Midterm

Student presentations:

Aaron Armstrong: (Aaron's slides)
H. Lipson, Evolutionary robotics and open-ended design automation

Montana Low (Montana's slides)
S. Forrest et al., Computation in the wild

Greg Nishikawa
S. Lucas and G. Kendall, Evolutionary computation and games
Fogel et al., A platform for evolving intelligently interactive adversaries

Review for midterm

Homework due: Homework 4.

Thursday, Oct. 26

Midterm exam


Tuesday, Oct. 31



M. Mitchell, Analogy-Making as a Complex Adaptive System

No homework this week --- work on your projects instead.

Thursday, Nov. 2

Analogy-making, continued

Knowledge representation

Student presentations:

Dora Raymaker: (Dora's slides
T. Evans, A program for the solution of a class of geometric analogy intelligence-test questions

Ki Yung Ahn: (Ki Yung's
B. Falkenhainer, K. D. Forbus, and D. Gentner, The structure mapping engine

Glen Sasek:

D. Chalmers, R. M. French, and D. R. Hofstadter, High-level perception, representation, and analogy: A critique of artificial intelligence methodology

K. Forbus et al., Analogy just looks like high level perception: Why a domain-general approach to analogical mapping is right


Tuesday, Nov. 7

Guest talk: Mick Thomure
Text classification (slides) and document retrieval (slides)

Knowledge representation (continued), information retrieval, and probabilistic reasoning

Reading: Textbook, Chapter 10, Section 6, Chapter 23, Section 2,

Homework assigned: Homework 5 (Information retrieval, knowledge representation, probabilisitc reasoning), due Tuesday Nov. 14.

Thursday, Nov. 9

Knowledge representation, information retrieval, and probabilistic reasoning, continued

Student presentations:

Alex Ten: (Alex's slides)
Callan et al. The INQUERY retrieval system

Tony Asche: (Tony's slides) q
A. Gupta and R. Jain, Visual information retrieval

J. Eakins et al., Similarity retreival of trademark images

Reading: Textbook, Chapter 13 (as needed); Chapter 14 (Sections 1-5)

Tuesday, Nov. 14

Probabilistic reasoning, continued

Student presentation:

Scott Merz: (Scott's slides)
Challenges in information retrieval and language modeling

Wiener et al. A neural network approach to topic spotting

Reading: Textbook, Chapter 15, Sections 1-3

Homework due: Homework 5.

Homework assigned: Homework 6 (Bayesian networks), due Tuesday Nov. 21.

Thursday, Nov. 16

Probabilistic reasoning, continued

Here are all the class lecture slides on probabilistic reasoning and Bayesian networks.

Student presentations:
Jeff Green: (Here are Jeff's Collaborative filtering with the simple Bayesian classifier

M. Sahami et al., A Bayesian Approach to Filtering Junk E-Mail

Kevin Magee (Here are Kevin's Combining approaches to information retreival

Nathan Clow: (Here are Nathan's Five useful properties of probabilistic knowledge representations from the point of view of intelligent systems


Tuesday, Nov. 21

Speech and Vision

Review for final exam

Student presentations:
Brian Rogers (Speech)
D. Stork et al., Neural network lipreading system for improved speech recognition

David Erwin (Speech) (Here are David's Large vocabulary continuous speech recognition: A review

Ian Elliot: (Here are Ian's Co-evolution of active vision and feature selection

Homework due: Homework 6.

Thursday, Nov. 23

Thanksgiving holiday


Tuesday, Nov. 28

Project presentations


Thursday, Nov. 30

Project presentations


Tuesday, Dec. 5

Finals week: No class


Thursday Dec. 7

Final exam, 10:15am-12:05pm

Final paper from project teams due Friday, December 8, by 5pm. Here is the required format for the final paper.