BU Logo

CAS CS 440/640 Artificial Intelligence - Fall 2007

Course Objectives - Course Materials - Requirements
Collaboration and Academic Integrity - Help - Schedule - Links


Lectures: Mon, Wed, Fri 1:00 - 1:50 pm in CAS 116
Instructor: Prof. Margrit Betke
Teaching Fellow: Vitaly Ablavsky
Class web page:
http://www.cs.bu.edu/faculty/betke/cs440
Class mailing lists:
cs440@cs.bu.edu and cs640@cs.bu.edu
Contact Information:
Staff Email Phone Office Hours Office
Margrit Betke betke@cs.bu.edu 353-8919 Thu 2-4, Fri 2-3, and by appointment MCS 286
Vitaly Ablavsky ablavsky@cs.bu.edu 358-1139 Tue 3-4, Wed 11-1 and by appointment MCS 263

Seeing Me in My Office:
Please feel free to stop by my office anytime. My office is in MCS 286 (111 Cummington St). I am generally around every day. I may be in meetings, so the best time to reach me is during office hours. You can also make an appointment by email. I'm happy to talk with you about the course, research in computer vision, machine learning, and pattern recognition, your plans for the future, or anything else. Check out my personal web page to get to know me a little.

Responsibilities of Teaching Fellow:
The Teaching Fellow is responsible for helping you out during his office hours, grading the written homeworks, and designing and grading the programming projects. Please contact him if you have questions about your homework grades.


Course Objectives

Our goal is to learn about computer systems that exhibit intelligent behavior, in particular, perceptual and robotic systems. Topics include human computer interfaces, computer vision, robotics, game playing, pattern recognition, knowledge representation, planning, and machine learning.

Prerequisites of CS440: Linear Algebra (CAS MA 242) or Geometric Algorithms (CAS CS 232), 1 Year Programming Experience (C, C++, or Java at CS112 level) or consent of instructor. Prerequisites of CS640: Same as above and BA background in Computer Science (e.g., Algorithms, Theory, Programming Languages).



Course Materials

Handouts: The updated course syllabus and most handouts are made available online. Check our course web page at least once a week for homework assignments and other information.

Textbook: Artificial Intelligence by Patrick H. Winston. Addison Wesley. ISBN: 0-201-53377-4.

Computing Environment: You will use the Computer Science Department's main server csa.bu.edu to download code and submit programming solutions. To get an account on csa, go to the Computer Science Department's Undergraduate Lab located at 730 Commonwealth Ave. You can work on various platforms in the lab there (and have immediate access to the computing staff). You can also access csa remotely using scp and ssh. I discourage the use of telnet and ftp due to security problems. Please add yourself to the appropriate course mailing list by typing csmail -a cs440 or csmail -a cs640 on csa. For the CS640 course projects, you can also use the Human-Computer Interface Lab in PSY 228A. If you want to use the lab for your project, talk to me first, since access to the lab is restricted.



Requirements

Class Participation: Come to class and participate regularly. Reading the assigned texts and listening in class will only give you a "passive understanding" of the material. I encourage discussions in class to help you acquire an "active understanding" of the material so that you can evaluate existing computer systems critically and learn to develop your own creative solutions.

Reading: To prepare for each class, you will be asked to read textbook chapters and journal papers, and explore web sites. You can achieve a good understanding and appreciation of the state-of-the-art in artificial intelligence if you read the assigned texts thoroughly.

Homework: The homework includes four programming assignments and several written problem sets. The due dates are listed below. Programs and reports must be submitted electronically. Guidelines for submission are provided with each assignment. Written homework must be handed in at the beginning of class. Late solutions will be levied a late penalty of 20% per day (up to three days). After three days, no credit will be given.

Project: A project is required for students enrolled in CS640. You can propose your own project topic or use one of my project suggestions. I will discuss your project's scope, design, and presentation with you in my office hours and provide guidance throughout the semester. Read the project guidelines carefully. You may work by yourself or in a group. You will present the final project in class at the end of the term. In the presentation, you should introduce the topic of the work, give a problem definition, explain the long-term and short-term goals, and discuss the motivation. Explain the algorithms and report on the experiments and results. How do they relate to previous work? Are they satisfactory? What are your conclusions? Give a critical evaluation. Is this promising work? Has it been successful? What are the limitations?
See me in my office hours to discuss your project well in advance of your presentation. With some additional work, you may be able to use your project to fulfill the project requirement in the BA/MA and MA programs. You may use the Human-Computer Interface Laboratory in PSY 228A to develop your project.

Colloquia: Students enrolled in CS440 and CS 640 are encouraged to attend the CS Department Colloquia. In addition to the CS Department Colloquium Series, you may also check out talks in other departments and at other universities. A partial list includes: BU College of Engineering Seminar Calendar , CSAIL lab at MIT , MIT Department of Electrical Engineering and Computer Science , Northeastern College of Computer and Information Science , Tufts Department of Computer Science Colloquium, UMass Boston Department of Computer Science. Students enrolled in CS 640 must attend three talks on subjects related to Artificial Intelligence and write a summary on each talk. The one-page review should give a problem definition, summarize the algorithms and results, and briefly explain how the work relates to material discussed in class. Reviews must be submitted at the beginning of class on the dates listed in the syllabus. Reviews should be checked for typographical and grammatical errors. Reviews that are late or contain errors will not receive the grade "A."

Exams: There will be two exams on the material discussed in the class and practiced with homeworks. The exams will be quite easy for students who come to class, participate in our discussions, and keep up with homework assignments and programming projects. The date of the midterm exam is Friday, October 19, 2007. The final exam will focus on material discussed in the second part of the course, but may also test earlier material. You are allowed to use one double-sided page of notes in each exam.

Grading Policy: Your final grade will be determined roughly as follows:

CS 440 CS 640
Midterm exam 20% 20%
Final exam 30% 30%
Programming Assignments 20% 10%
Written Problem Sets 20% 10%
Class participation 10% 10%
Project and presentation 0% 15%
Talk reviews 0% 5%



Collaboration and Academic Integrity

You are encouraged to collaborate on the solution of the homework. If you do, you must code up your solutions on your own and acknowledge your collaborators. Each student must submit his or her own electronic version of the solutions. CS640 students may request an exception to this rule for their final project. If you use algorithms or code that are not your own original work and that were not provided in class or discussed in the textbook, you must give a detailed acknowledgment of your source.

Cheating and plagiarism are not worthy of Boston University students. We expect you to abide by the rule stated above and the standards of academic honesty and computer ethics policy described in http://www.bu.edu/computing/ethics/ .



Help

Artificial Intelligence is an elective course that will introduce you to an exciting topic in computer science. It should be fun and not too much of a struggle for you. Make sure that you have had the prerequisites. Depending on your level of programming experience and/or mathematics background, the course may be challenging for you. If you do not understand the material, ask for help immediately. Ask questions in class. If one student is confused about something, then maybe others are also confused and grateful that someone asked. Please come and see me or Vitaly for help or send us email. Our task is to help you learn a very interesting topic.


Course Schedule

Dates Topics Readings Homework Programming
Projects
WF 9/5-7 Introduction - What is AI? Smart Rooms, The Kids Room Bobick . .
M-M 9/10-9/17 Computer Vision (e.g., face detection, binocular and photometric stereo). Last day to ADD class: M 9/17 Ch. 27 H1 out (9/12) P1 out (9/12, 1 1/2 weeks)
WF 9/19-21 Neural Nets: Introduction Ch. 22 H1 due (9/19) , H2 out P1 due (9/21)
MWF 9/24-28 Neural Nets: Backpropagation Ch. 22 H2 due (9/28) P2 out (9/21, 2 weeks)
MWF 10/1-5, T 10/9, W 10/10 Applications of Neural Nets, Face Recognition, Markov Models, Hidden Markov Models with Discrete Observations
Last Day to DROP Classes (without a 'W' grade) or change from Credit to Audit: Tu 10/9
Sirovich, Turk, Rabiner H3 out (10/5) P2 due (10/5), P3 out (10/5, 3 weeks)
FMW 10/12-17 HMMs with Continuous Output Densities
Applications of HMMs: Speech and ASL
Rabiner, Vogler H3 due (10/12), CS640:Review-1due (10/10) .
F 10/19 Midterm Exam . . .
MWF 10/22-26 Search Techniques: Branch-and-Bound, A*, Robot Path Planning
Last Day to DROP Classes (with a 'W' grade): F 11/9
Ch. 5 . P3 due (10/26)
MW 10/29-31, FM 11/2-5
Game Playing: Minimax, Alpha-Beta Ch. 6 . P4 out (11/2,
2 1/2 weeks)
WFW 11/7-14 Expert Systems
No class on M 11/12.
Ch. 7 H4 out (11/9), CS640: Review-2 due (11/7), .
F 11/16, M 11/19, M 11/26 Logic, Planning
No class on WF 11/21,23, Thanksgiving Holiday
Ch. 13 and Ch. 15 H4 due (11/16) P4 due (11/21)
WF 11/28-30 Planning, Natural Language Processing Handout of Slides H5 out (12/5) .
MWF 12/3-7 Robotics, Human-Computer Interfaces Handout of Slides CS 640: Review 3 due (12/7) .
MW 12/10-12 CS 640 Course Projects . H5 due (12/12) .
W 12/19, 12:30-2:30 pm Final Exam . . CS 640 projects due (12/17).

The syllabus may change depending on the time spent on different topics and whether new or alternative subjects are discussed. Suggestions are welcome!


Homework Solutions

Solutions to the written homework are handed out in class. If you miss them, you can find them on the shelf marked "CS 440/640" located across MCS 135.

Programming Assignment results,
Game Tournament Results


CS 640 Project Suggestions


Related Papers and Web Sites


Links

Check out http://www.cs.bu.edu/faculty/betke/links.html if you need ideas for your class project, if you are looking for a job, or if you are interested in research related to AI and computer vision. You will find a list of links to conferences, journals, research groups, and companies.

Images of AI Research
Margrit Betke, Associate Professor
Computer Science Department
Boston University
111 Cummington Street (campus map)
Boston, MA 02215
Email: betke@cs.bu.edu
URL: http://www.cs.bu.edu/faculty/betke
Phone: 617-353-8919, Fax: 617-353-6457
Last updated: September 4, 2007