CS 440
Introduction to Artificial Intelligence
Fall 2003
Mon & Wed 4:30-5:50 PM ARC-105
Wed 6:35-7:30 PM ARC-105
Basics
Instructor
Vladimir Pavlovic
Office: 312 CoRE
Email: vladimir@cs.rutgers.edu
Web: www.cs.rutgers.edu/~vladimir
Phone: 732-445-2654
Office hours: Mon, 3:00-4:00
TA
Zhi Wei
Office: 416 Hill
Email: zhwei@paul.rutgers.edu
Phone: 732-445-6996
Office hours: Thu, 4:30-6:30 PM
Mailing List
CS440-FALL03@rams.rutgers.edu
List archive.
Textbook
Russell & Norvig, "Artificial Intelligence: A Modern Approach", 2nd
Edition, Prentice Hall, 2003. Also referred to as AIMA.
Organization
Lectures are on Mon and Wed, 4:30-5:50 PM in ARC-105.
Discussion session is on Wed, 6:35-7:30 PM in ARC-105.
Prerequisites
CS314 (Principles of
Programming Languages). You also need a solid knowledge of
calculus. Some knowledge of probability and linear algebra will
be beneficial.
Grading
Homework
|
25%
|
Presentations
|
15%
|
Midterm
|
30%
|
Final
|
30%
|
Syllabus
This is an introductory AI course. As such, it will cover, in
some depth, a wide range of AI topics:
- Search,
- Knowledge representation,
- Planning,
- Uncertainty,
- Learning, and
- Examples and applications in speech and language modeling, visual
perception, medical informatics, and robotics.
Detailed syllabus can be found here.
Homework
Assignments are due by the end of lecture on the day indicated.
Your are expected to turn in
your assignments on time.
Late homework
will not be accepted!
Homework will be
assigned on weekly/bi-weekly basis.
Homework accounts for 25% of the final grade.
Homework are to be done individually. You are encouraged to
discuss assignments but the solutions you turn in should be yours. Copying of
solutions will not be tolerated and will be immediately
sanctioned. Please see Rutgers
Policy on Academic Integrity.
Homework scores
Homework scores are here and
here (graphical).
Projects
Presentation/projects will be given throughout the semester by teams of
students. Each team will consist of two students.
Presentations will cover specialized subtopics of the topics presented
in class (e.g., Bayesian network software.) The team will be in
charge of researching the presentation topic and preparing a 15min
presentation. A copy of the presentation will be posted on this
web site. You will need to use the textbook as well as additional
resources (books, papers, etc.)
The team members will be assigned randomly. Each student will
have to participate in one presentation during the semester.
I will assign the presentation topic to the team two weeks before the
presentation is due.
If you want to use my laptop for the presentation, you will be
responsible
for getting the presentation to me in time sufficient for me to place
it on the laptop (2 hours before the class meets.)
Tests
All tests will be closed-book, closed-notes.
As with the homework assignments, you are expected to do your tests on
your own. Please follow the same standards of Academic
Integrity.
Midterm. Oct. 20, 4:30pm, ARC-105.
Problems
Solutions
Scores
Stats
Final. Dec. 17, 8:00am-11:00am, ARC-105.
Computing
We will use a combination of Java and MATLAB for programming
assignments.
We may use O'Caml and Lush.
Resources
AIMA web site.
Kevin Murphy's Bayesian
network page.
Useful matrix
and Gaussian identities by Sam Roweis.
Matlab
Documentation from Mathworks.
Tutorial from MTU.
Tutorials from University of
Colorado.
Probabilistic
Modeling Toolkit.