|
15-381 Artificial Intelligence:
|
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.
Class lectures: Tuesdays & Thursdays 1.30pm-2:50pm, Wean Hall 7500 starting on Tuesday January 16th, 2007
Instructors:
- Martial Hebert, NSH 4101,
x8-2585, Office hours: Friday 10am - noon
- Mike Lewicki, Mi 115K,
x8-3921, Office hours: Wednesday 10am - noon
Note: if you find the doors in NSH or EDSH are locked after 5pm, please contact the TAs via phone so that we can open the door for you. Class Assistant:
|
Mailing Lists:
- The instructor + TA mailing list is instructors-15381-s07 (at) mailman.srv.cs.cmu.edu
- The class mailing list is 15381-s07 (at) mailman.srv.cs.cmu.edu. If you have not been added to the list by now, please contact Gil (egjones+@cs.cmu.edu).
Textbook:
- Recommended (optional) textbook: Russell and Norvig's "Artificial Intelligence: A Modern Approach".
- Recommended (optional) second textbook (if you decide you want two): Pattern Classification (2nd Edition), Duda, Hart and Stork.
Other resources:
- http://aima.cs.berkeley.edu
- http://www.autonlab.org/tutorials
Grading:
- Final grades will be based on homework (40%), midterm (20%), and final exam (40%).
Policy on late homework:
Homework must be handed in at the start of class (1.30pm) on the due date.
- If it is between 0-24 hours late it will receive 90% of its score.
- If it is between 24-48 hours late it will receive 50% of its score.
- If it is more than 48 hours late it will receive no score.
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
- not explicitly tell each other the answers
- not to copy answers
- not to allow your answers to be copied
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.
Review Sessions
|
Day & Time: |
Tuesday 6:00pm-8:00pm |
|
Location : |
WeH 4623 |
|
Date: |
Announced in class and on the website |
There will be occasional optional review sessions on Tuesday 6:00pm-8:00pm in
WeH 4623, often used for things like Q&A for assignments and reviewing
material for exams. Please check the website for information on upcoming review
sessions.
Homework assignments
Assignments will be available for downloading on the specified dates. Please contact the grader listed for a particular question if you have concerns regarding the scoring of that question.
|
|
Links |
Out |
Return |
Solutions |
|
HW1 |
Tue Jan. 23 |
Tue Feb. 6 |
Homework 1 solutions Graders |
|
|
HW2 |
hw2.pdf |
Tue Feb. 6 |
Tue Feb. 20 |
Homework 2 solutions Graders |
|
HW3 |
hw3.pdf |
Tue Feb. 20 |
Tue Mar. 20 |
Homework 3 grade distribution Graders |
|
HW4 |
Tue Mar. 20 |
Tue Apr. 3 |
Homework 4
Solutions Homework 4 grade distribution Graders |
|
|
HW5 |
Tue Apr. 3 |
Tue Apr. 17 |
Homework 5 grade distribution Graders |
|
|
HW6 |
Tue Apr. 17 |
Tue May 1 |
Graders |
Syllabus
|
Date |
Topic |
Chapter |
Notes |
Links/Slides |
|
|
|
|
|
|
|
Jan. 16 |
Intro |
|
|
|
|
|
SEARCH |
|
|
|
|
Jan. 18 |
Search |
3 |
|
|
|
Jan. 23 |
Search |
3 |
HW1 out |
|
|
Jan. 25 |
Search: Hill Climbing, Stochastic Search, Simulated Annealing |
3,4 |
|
|
|
Jan. 30 |
Search: Hill Climbing, Stochastic Search, Simulated Annealing |
3,4 |
HW1 review |
|
|
Feb. 1 |
Constraint Satisfaction Problems |
5 |
|
|
|
Feb. 6 |
Constraint Satisfaction Problems |
5 |
HW1 due; HW2 out |
|
|
Feb. 8 |
Robot Motion Planning |
25 |
|
|
|
|
GAME THEORY |
|
|
|
|
Feb. 13 |
Algorithms for Playing and Solving Games |
6 |
HW2 review |
|
|
Feb. 15 |
Games with Hidden Information |
6 |
||
|
Feb. 20 |
Non-Zero-Sum Games |
6 |
HW2 due; HW3 out |
|
|
Feb. 22 |
Game Theory, continued |
6 |
|
|
|
Feb. 27 |
Auctions and Negotiations |
6 |
HW3 review |
|
|
|
SYMBOLIC REASONING |
|
|
|
|
Mar. 1 |
Automated Theorem Proving with Propositional Logic |
8,9 |
||
|
Mar. 6 |
Reasoning, Cont. |
11 |
Midterm review |
|
|
Mar. 8 |
Midterm Exam |
|
Midterm |
Previous Exams:
S06-sols Solutions: S07-sols Graders |
|
Mar. 13/15 |
Midterm Break |
|
|
|
|
|
PROBABILISTIC REASONING |
|
|
|
|
Mar. 20 |
Probability and Uncertainty |
HW3 due; HW4 out |
||
|
Mar. 22 |
Probability and Uncertainty |
|
||
|
Mar. 27 |
Bayes Nets |
14 |
HW4 review |
|
|
Mar. 29 |
Bayes Nets |
14 |
||
|
Apr. 3 |
Markov Decision Processes |
16,17 |
HW4 due; HW5 out |
|
|
Apr. 5 |
Markov Decision Processes |
16,17 |
|
|
|
|
LEARNING |
|
|
|
|
Apr. 10 |
Intro + Decision Trees |
18 |
HW5 review |
|
|
Apr. 12 |
Decision Trees (cont.) |
18 |
||
|
Apr. 17 |
Probabilistic Learning and Naive Bayes |
20 |
HW5 due; HW6 out |
|
|
Apr. 19 |
No class (carnival) |
|
||
|
Apr. 24 |
Neural Networks |
20 |
|
|
|
Apr. 26 |
Clustering and Cross Validation |
14 |
|
|
|
May 1 |
Reinforcement Learning |
21 |
HW6 due |
|
|
May 3 |
Reinforcement Learning |
21 |
|
|
|
May 11 |
Final Exam |
|
05:30pm-08:30pm |
Previous Exams:
S05-sols Solutions: |