15-381 Artificial Intelligence, Spring 2006
Martial Hebert |
This class is all about autonomy: how can machines make their own decisions and make them well? The goal is that by the end of the class you will be an expert in a wide range of useful technologies for automated decision making. You'll have seen practical examples of putting AI into commercial, scientific, federal and consumer applications. And hopefully you'll be ready to find new AI technologies and applications.
We will not stick strictly to the traditional definitions of AI, but will cover technologies from a wider range of disciplines that your instructor believes are most important for practical autonomous decision-making.
Incoming students need to be proficient with the theory and practice of algorithms and programming: 15-212 is a prerequisite.
Class lectures: Tuesdays & Thursdays 1.30pm-2:50pm, Wean Hall 7500 starting on Tuesday January 17th, 2006
Instructor:
|
Textbook:
Grading:
Policy on late homework:
Homework must be handed in at the start of class (1.30pm) on the due date.
Policy on collaboration:
You are encouraged to discuss the general algorithms and ideas in the class in order to help each other answer homework questions. You are also welcome to give each other examples that are not on the assignment in order to demonstrate how to solve problems. But we require you to
This policy is in order to be fair to the rest of the students in the class. We will have a grading policy of watching for cheating and we will follow up if it is detected. Some assignments will allow you to form teams of two people. In that case you will submit one paper on behalf of the partnership, and partners may explicitly help each other out with answers, but the above anti-copying rules still apply between teams.
Day & Time: |
Tuesday 6:00pm-8:00pm |
Location : |
WeH 5409 |
Date: |
Announced in class and on the website |
There will be occasional optional review sessions on Tuesday 6:00pm-8:00pm in
WeH 5409, often used for things like Q&A for assignments and reviewing
material for exams. Please check the website for information on upcoming review
sessions.
Assignments will be available for downloading on the specified dates.
|
Links |
Out |
Return |
Solutions |
HW1 |
Tue Jan. 24 |
Tue Feb. 7 |
||
HW2 |
Tue Feb. 7 |
Tue Feb. 21 |
||
HW3 |
Tue Feb. 21 |
Tue Mar. 7 |
||
HW4 |
Tue Mar. 7 |
Thu Mar. 30 |
||
HW5 |
Thu Mar. 30 |
Thu Apr. 13 |
||
HW6 |
Tue Apr. 17 |
Tue May 2 |
Date |
Topic |
Chapter |
Notes |
Links/Slides |
|
|
|
|
|
Jan. 17 |
Intro |
|
|
|
|
SEARCH |
|
|
|
Jan. 19 |
Search |
3 |
|
|
Jan. 24 |
Search: Hill Climbing, Stochastic Search, Simulated Annealing |
3,4 |
HW1 out |
|
Jan. 26 |
Search: Hill Climbing, Stochastic Search, Simulated Annealing |
3,4 |
|
|
Jan. 31 |
Constraint Satisfaction Problems |
5 |
HW1 Review |
|
Feb. 2 |
Constraint Satisfaction Problems |
5 |
|
|
Feb. 7 |
Robot Motion Planning |
25 |
HW1 due; HW2 out |
|
Feb. 9 |
Robot Motion Planning |
25 |
|
|
|
GAMES |
|
|
|
Guest Lecturer: Stephen Smith |
25 |
HW2 Review |
|
|
Feb. 16 |
Algorithms for Playing and Solving Games |
6 |
|
|
Feb. 21 |
Games with Hidden Information |
6 |
HW2 due; HW3 out |
|
Feb. 23 |
Non-Zero-Sum Games |
6 |
|
|
Feb. 28 |
Auctions and Negotiations |
6 |
HW3 Review |
|
|
REASONING |
|
|
|
Mar. 2 |
Automated Theorem Proving with Propositional Logic |
8,9 |
|
|
Mar. 7 |
Reasoning, Cont. |
11 |
HW3 due; HW4 out |
|
Mar. 9 |
Midterm Exam |
|
Midterm |
Previous Exam: S05, S05-sols Review Slides: Midterm Solution: |
Mar. 14/16 |
Midterm Break |
|
|
|
|
LEARNING |
|
|
|
Mar. 21 |
Intro: Uncertainty and Probabilistic Learning |
18 |
|
|
Mar. 23 |
Decision Trees |
18 |
|
|
Mar. 28 |
Decision Trees (cont.) |
18 |
HW4 Review |
|
Mar. 30 |
K-Means |
20 |
HW4 due; HW5 out |
|
Apr. 4 |
Neural Networks |
20 |
|
|
Apr. 6 |
Neural Networks |
20 |
HW5 Review |
|
Apr. 11 |
Cross-Validation & Intro Bayes Net |
14, 20 |
|
|
|
REASONING WITH UNCERTAINTY |
|
|
|
Apr. 13 |
Bayes Nets |
14 |
HW5 due; |
|
Apr. 18 |
Bayes Nets |
14 |
HW6 out |
|
Apr. 20 |
No Class |
|
|
|
Apr. 25 |
Markov Decision Processes |
16,17 |
HW6 Review |
|
Apr. 27 |
Markov Decision Processes |
16,17 |
|
|
May 2 |
Reinforcement Learning |
21 |
HW6 due |
|
May 4 |
Reinforcement Learning |
21 |
|
|
May 12 |
Final Exam |
|
8:30a.m.-11:30a.m. |
Previous Exam: |