Artificial Intelligence

CS 441/541
Artificial Intelligence
Fall Quarter 2011


Time : Mondays and Wednesdays, 2:00-3:50pm
Location: Fourth Avenue Building (FAB), Room 40-07.

Instructor: Melanie Mitchell, FAB 120-24, (503) 725-2412, mm-AT-cs.pdx.edu.
Office hours: Tu,Th 3:00-4:00pm, or by appointment.

Teaching Assistant: Josh Hughes
Office hours: M,W 4:00-5:00pm, or by appointment. Office hours will be held in the CS department fishbowl.

Course Website: :
http://www.cs.pdx.edu/~mm/AIFall2011/index.html

Prerequisites: CS 202, 311, or equivalent, or permission of instructor.

Textbook: None. Instructor will assign readings available on-line.

Major Topics: Problem-solving and game-playing as search, natural-language processing, learning, vision, reasoning under uncertainty, analogy-making, robotics, history and philosophy of AI.

Assignments: Along with assigned reading, there will be six homework assignments on different topics covered in class, each with both written and programming components. In addition, each graduate student (including post-bacs) in the class will read a recent published paper on a chosen topic and give a 10-minute in-class presentation on that paper.

Exams: There will be four in-class quizzes to test basic understanding of the material presented in class and in the readings.

Grading, Undergraduates: Homework: 60% (six assignments, each weighted equally). Quizzes (four quizzes): 40%.

Grading, Graduate Students (including post-bacs): Homework: 50% (six assignments, each weighted equally). Quizzes (four quizzes): 40%. In-class presentation: 10%.

Academic integrity: Students will be responsible for following the PSU Student Conduct Code.

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

Syllabus (subject to change):

Date

Topics

Homework and Reading

Monday Sept. 26

Class overview
History of AI
Current state of AI
Problem-solving as search, part I.

Here are the slides: pptx or pdf.

Reading:

Alan Turing, Computing Machinery and Intelligence

Kapor-Kurzweil Bet

Homework 1, due Monday, Oct. 3.

Wednesday Sept. 28

Problem-solving as search, Part II

Here are the slides: pptx or pdf.

Reading: Class notes (slides) on problem-solving as search

Monday Oct. 3

Game-playing I

Here are the slides: pptx or pdf.

Reading: Class notes on game-playing

Homework 2, due Wednesday, Oct. 12.

Wednesday Oct. 5

Game-playing II (Guest lecturer: Prof. Bart Massey)

Here are Bart's slides

Here is the worked out example of alpha-beta search that we went over in class

Here is the study sheet for the first quiz (on Monday 10/10).

Monday Oct. 10

Quiz 1

Natural language processing I: Text analysis

Here are the NLP Intro slides: pptx or pdf.

Here are the NLP N-Gram slides: pptx or pdf.

Reading: Chapter 1 from Jurafsky and Martin, Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition

Cavnar and Trenkle, N-gram-based text categorization

Manning, Raghavan, and Schutze, Text classification and Naive Bayes, pp. 253-270 (Chapter 13 in Introduction to Information Retrieval)

Homework 3, due Wednesday, Oct. 26

Wednesday Oct. 12

Student presentations:
Nathan Nifong will present: The Learning Behind Gmail Priority Inbox

Matthaus Litteken will present: A survey: Algorithms simulating bee swarm intelligence

Natural language processing II: Text analysis, continued.

Here are the NLP Naive Bayes slides: pptx or pdf.

Monday Oct. 17

Natural language processing III: Vector space models, latent semantic analysis, and question-answering.

Here are the slides: pptx or pdf.

Reading: D. Ferrucci et al. Building Watson: An overview of the DeepQA project

Optional Reading:
B. Christian, Mind vs. Machine

E. Brill, S. Dumais, and M. Banko, An analysis of the AskMSR question-answering system

Wednesday Oct. 19

Student presentations:

John Ledesma will present Minds, Brains, and Programs by John Searle

Max Garvey will present: Fingerprinting to identify repeated sound events in long duration personal audio recordings by James P Ogle and Daniel PW Ellis

Natural language processing IV: Question answering, continued; machine translation

Here are the machine translation slides: pptx or pdf.

Reading:
P. F. Brown et al., A statistical approach to machine translation

Optional Reading:
D. Bellos, I, Translator

T. Adams, Can Google break the computer language barrier?

Monday Oct. 24

Student presentations:

Mike Flakus will present: Video-Based Lane Estimation and Tracking for Driver Assistance: Survey, System, and Evaluation

Sarah Cathay will present: SVM-Based Multi-Modal Classification of Activities of Daily Living in Health Smart Homes: Sensors, Algorithms and First Experimental Results

Learning I: Support vector machines

Here are the SVM slides: pdf.

Here is the study sheet for the second quiz (on Monday 10/31).

Reading:
M. A. Hearst et al. Support Vector Machines. IEEE Intelligent Systems, 18-28, July/August 1998.

Wednesday Oct. 26

Student presentations:

Jessica Fortier: A Recommender System for On-line Course Enrolment: An Initial Study

Learning II: Hidden Markov Models (and applicaitons to speech recognition)

Here are the speech-recognition slides: pptx or pdf.

Reading: A. L. Buchsbaum and R. Giancarlo, Algorithmic aspects in speech recognition: An introduction, Sections 1-4 (to p. 21).

Homework 4, due Wednesday Nov. 9.

Here is the link to SVM_light

Here is SpamExamples.txt

Monday Oct. 31

Quiz 2

Learning III: Neural networks Here are the neural networks slides: pptx or pdf.

Reading: Course slides on neural networks

Wednesday Nov. 2

Student presentations: Mandar Patil

Learning VI: Neural networks, continued

Here is the Notes on Naive Bayes document: pdf

Here is the Notes on Perceptrons document: pdf

Monday Nov. 7

Learning V: Genetic algorithms

Here are the GA slides (part 1): pptx or pdf

Student presentations:

Charles Capps: Cooperative self-organization in a heterogeneous swarm robotic system

Zach Greenvoss: Narrative planning: Balancing plot and character.

Reading: Course slides on genetic algorithms

Wednesday Nov. 9

Genetic algorithms, continued

Here are the GA slides (part 2): pptx or pdf

Student presentations:

Betsy Rubina Kavali: Detecting Faces in Images: A Survey

Shaun Brandt: Information Extraction from Wikipedia: Moving Down the Long Tail

Monday Nov. 14

Vision I

Here are the Vision, Part 1 slides: pptx or pdf

Here are the Vision, Part 2 slides: pptx or pdf

Here is the study sheet for the third quiz (on Monday 11/21).

Reading: C. B. Akgul et al., Content-based image retrieval in radiology: Current status and future directions

T. Serre, L. Wolf, and T. Poggio, Object recognition with features inspired by visual cortex

Homework 5, Due Monday, Nov. 28:

Homework 5, Part 1 (Neural Networks)

Homework 5, Part 2 Genetic Algorithms.

Here is the gzipped tarball with the neural network code.

Here is the gzipped tarball with the genetic algorithm code.

Here is the RobbyGraphics package in Netlogo.

Here are the instructions for the RobbyGraphics package.

Here is a link to download Netlogo.

Wednesday Nov. 16

Vision II (Guest lecturer: Will Landecker)

Monday Nov. 21

Quiz 3

Analogy and Metaphor

Here are the Analogy slides: pptx or pdf

Reading: D. Hofstadter and M. Mitchell, The Copycat project: A model of mental fluidity and analogy-making

Wednesday Nov. 23

Analogy and Metaphor, part 2

Here are the "Metaphors We Live By" slides: pptx or pdf

Here are the Petacat slides: pptx or pdf

Student presentations:

James Holladay: Best-First Heuristic Search for Multi-core Machines

Kirk Bowers: Temporal Difference Learning and TD-Gammon

Monday Nov. 28

Robotics

Here are the slides: pptx or pdf

Student presentations:

Murali Gurudath: Digital Intuition: Applying Common Sense Using Dimensionality Reduction

Michael Novak: Grammar-Based Random Walkers in Semantic Networks

John Balwit: Resilient Machines Through Continuous Self-Modeling

Reading: S. Thrun, Toward Robotic Cars

C. Breazeal, Toward Sociable Robotics

Homework 6. Due Friday Dec. 9, 5pm.

Wednesday Nov. 30

Quiz 4: Optional. This quiz will be take-home, open-book. It will cover some subset of the material from previous quizzes. It is optional -- if you're happy with your quiz scores so far, you don't need to take it. Due Friday Dec. 2 by 5pm.

AI future and ethics

Here are the slides: pptx or pdf

Kurzweil talk slides

Reading:

R. Kurzweil, The Singularity is Near: Book Precis

D. McDermott, Kurzweil's argument for the success of AI (You need to be on the PSU network to download this paper)

B. Joy, Why the future doesn't need us

Monday Dec. 5

No class (finals week).

Wednesday Dec. 7

No class (finals week).