6.825: Techniques in Artificial Intelligence--Fall '04

Announcements
References
Syllabus
Description
Prerequisites
Grading
Collaboration
Previous Editions


Course Staff Lectures

Professor: Leslie Pack Kaelbling
lpk@csail.mit.edu
Office: 32-G486
Office Hours: by appointment

TA: Sanmay Das
6825-staff@csail.mit.edu
Office: E25-217 + [instructions]
Office Hours: Tuesdays, 2-4pm in 32-D451 and by appointment.

TA: Tomas Izo
6825-staff@csail.mit.edu
Office: 32-D542
Office Hours: Thursdays, 3-5pm in 32-397
You can also drop by my office or make an appointment.

Tuesdays and Thursdays,
9:30 - 11:00 am
Location: 2-190

Announcements

  • Exam Preparation Resources:
    • Updated past exams page.
    • Exercises posted on the syllabus page.
    • Sanmay's office hours: Friday, Dec 10, 2-4pm, 32-G451
    • Tomas' office hours: Sunday, Dec 12, afternoon. Check here for details (to be arranged).
  • Solutions to the quiz are online.
  • Our final exam has been scheduled for Monday Dec 13, 1:30 - 4:30 PM in DuPont.
  • There is a small bug in the unification algorithm in the textbook. Read this page for clarification.

References

Syllabus

Includes pointers to required reading not in the textbook and suggested exercises.

Description

6.825 is a graduate-level introduction to artificial intelligence. Topics include: representation and inference in first-order logic; modern deterministic and decision-theoretic planning techniques; basic supervised learning methods; and Bayesian network inference and learning.

Prerequisites

  • 6.041 (Probabilistic Systems Analysis)
  • 6.042 (Mathematics for Computer Science)
  • 6.046 (Introduction to Algorithms) (desirable, but not required)

Students should be familiar with uninformed search algorithms (depth-first and breadth-first methods), discrete probability (random variables, expectation, simple counting), propositional logic (boolean algebra), basic algorithms and data structures, basic computational complexity, and basic calculus. Students should also be aware that course assignments will require the use of the Java programming language.

Grading

The work for this course will consist of three take-home project assignments and two exams: a quiz and a final. The projects will count for 60% of the grade (20% each), and the exams, 40% (15% for the quiz and 25% for the final).

Late Policy for Projects: 10% off for each calendar day late. No credit if more than 5 days late.

Collaboration

We want to strongly encourage collaboration as a way for students to come to understand the material better. Project 1 is an individual assignment, but you may do Project 2 and Project 3 in groups of two, turning in a single write-up. You do not have to partner with the same person for both of the projects and you can choose to do either or both of them on your own.

If you are looking for a partner for an assignment, email the class list asking if anyone is available. You are also quite welcome to discuss the assignments as much as you'd like between groups. The ultimate requirement is this: Don't put your name on anything you don't understand. There will, of course, be no collaboration allowed on the exams.