CMPSCI 383: Introduction to Artificial Intelligence

• Fall 2011; Tuesday and Thursday, 9:30-10:45 • CMPS 142

Instructor

Andrew Barto
barto at cs.umass.edu
(413) 545-2109
Office: CMPS 272
Office hours -Tuesday and Thursday 11:00-12:00, or by appointment

Teaching Assistant

Philip Thomas
pthomas at cs.umass.edu
Office hours - Monday 10:00-11:00, Wednesday noon-1:00 in LGRT 220

Prerequisites

(CMPSCI 187 or CMPSCI 220 or CMPSCI 291SP) and (CMPSCI 240 or CMPSCI 311)

Reading Materials

Textbook: Artificial Intelligence: Artificial Intelligence: A Modern Approach, Third Edition by Stuart Russell and Peter Norvig. You must use the third edition of this book. This book's website contains lots of useful information and links: be sure to check it out. The UMass Text Annex will be displaying a digital option through CafeScribe, along with new, used and rental copies of the book for the start of classes. The book's website lists other e-book options.

Description

The Course explores key concepts of artificial intelligence, including problem solving, heuristic search techniques, game playing, automated planning, reasoning under uncertainty, decision theory and machine learning. We will examine how these concepts are applied in the context of several applications.

Grading

Homework assignments (5 or 6): 45%
Midterm: 20%
Final Exam: 25%
Class Participation: 10%

Exams

Exams will be closed book and closed notes. They will focus on conceptual understanding of key ideas from the course, including algorithms, data structures, and ability to match algorithms and data structures to actual problems. Each exam will be preceded by a review session. If you have any special needs/circumstances pertaining to an exam, you must talk to the instructor before the exam.

Assignment Policy

Assignments are to be handed in in class, or in the main office of the Computer Science building by 4:00 PM on the due date. A total of five extension days which can be applied to any combination of homework assignments during the semester without penalty. Additional extensions will be granted only due to serious and documented medical or family emergencies.

Regrade Policy

Homework assignments and tests will be returned in class. If you think a grading error was made on an assignment or test, or if you do not get the assignment or test handed back to you, you must talk to the TA or the instructor within a week of when it was handed back.

Academic Honesty Policy

Cheating is usually the result of other problems in school. Please come see the instructor or the TA anytime if you are unable to keep up with the work for any reason and we will work something out. We want to see you succeed and will do everything we can to help you out!

Instances of academic dishonesty will result in a zero on the project in question and initiation of the formal procedures: see the Academic Honesty and Appeals Procedure; be sure to look at Appendix B which gives examples of academic dishonesty.

Specifically, for this course, and in addition to the instances on that web site, all examinations, programming assignments, and written homeworks must be done individually. Code for programming assignments must not be developed in groups, nor should code be shared. You are encouraged to discuss with your peers, the TA or the instructor ideas, approaches and techniques broadly, but not at a level of detail where specific implementation issues are described by anyone.

If you have any questions on this, please ask the instructor before you act.

Tips for Doing Well

Read assigned text before class.
Begin assignments early.
Take notes.
Slides will be online, but they are only reminders of real content which is given verbally and on the board.
Be active.
Participate in discussion during class.
Ask questions.
Take advantage of office hours.

Disability Services

If you have a disability that requires any sort of accommodation to allow you to fully participate in this course, you should contact Disability Services.

Problem Sets

Problem Set 1

Problem Set 2, Othello source code

Problem Set 3

Problem Set 4

Problem Set 5

Schedule (subject to change)
Date Lecture topic Reading New assignments Assignments due
Sept. 6 Lecture 1 Slides
Introduction: What is Artificial Intelligence?
1.1 - 1.5
(read this before the midterm)
Answer questionnaire
Sept. 8 Lecture 2 Slides
Intelligent Agents
2.1 - 2.5
Questionnaire
Sept. 13 Lecture 3 Slides
Philosophical Foundations
26.1 - 26.4
Sept. 15 Lecture 4 Slides
Problem Solving as Search
3.1 - 3.4
Problem Set 1
Sept. 20 Lecture 5 Slides
Heuristic Search
3.5 - 3.7
Sept. 22 Lecture 6 Slides
Local Search
4.1 - 4.2
Sept. 27 Lecture 7 Slides
Local Search using Nondeterministic Actions and Partial Observations; Online Search
4.3, 4.4, 4.5
Sept. 29 Lecture 8 Slides
Adversarial Search
5.1 - 5.4
Recommended reading:Samuel,Schaeffer
Problem Set 2, Othello source code Problem Set 1
Oct. 4 Lecture 9 Slides
More on Adversarial Search: Stochastic Games
5.5 - 5.9
Recommended reading:TD-Gammon
Oct. 6 Lecture 10 Slides
Constraint Satisfaction
6.1, 6.2
Oct. 11 MONDAY CLASS SCHEDULE
Oct. 13 Lecture 11 Slides
More Constraint Satisfaction
6.3 - 6.6
Oct. 18 Lecture 12 Slides
Review for Midterm
Problem Set 2
Oct. 20 *************************
IN CLASS MIDTERM
*************************
Oct. 24 Lecture 13 Slides
Uncertainty
13.1 - 13.7
Oct. 27 Lecture 14 Slides
Bayesian Networks
14.1 - 14.3 Problem Set 3
Nov. 1 Lecture 15 Slides
Inference in Bayesian Networks
14.4, 14.5
Nov. 3 Lecture 16 Slides
Making Rational Decisions
16.1 - 16.4
Nov. 8 Lecture 17 Slides
Making Decisions over Time
17.1 - 17.3
Nov. 10 Lecture 18 Slides
Learning from Examples
18.1 - 18.4
Nov. 15 Lecture 19 Slides
Linear Regression and Classification
18.6 Problem Set 4 Problem Set 3
Nov. 17 Lecture 20 Slides
Neural Networks and Nonparametric Models
18.7, 18.8
Nov. 22 Lecture 21 Slides
Learning Probabilistic Models
20.1 - 20.4 Problem Set 5
Nov. 24 THANKSGIVING VACATION
Nov. 29 Lecture 22 Slides
Reinforcement Learning
Material useful for HW 5
21.1 - 21.3
Dec. 1 Lecture 23 Slides
More Reinforcement Learning
21.4 - 21.7
Dec. 6 Lecture 24 Slides
Review I
Problem Set 4
Dec. 8 Lecture 25 Slides
Review II
Problem Set 5
Dec. 12 ***************
FINAL EXAM
***************
8:00 am, LGRT0103