As we will see throughout the course, AI is not a field in which there is a set of neatly defined problems to solve, nor one in which it is obvious what constitutes a solution. Consequently, learning about AI involves not only learning about methods but also developing a viewpoint on what constitutes an AI question, how to define AI questions, which AI questions to explore, and how to recognize good answers. Rather than simply learning the approaches, we will be thinking critically about their goals and methods, analyzing their strengths and weaknesses, and attacking AI problems to find ways to improve them.
This course is designed to emphasize research skills and critical thinking, and to explore the state of the art in knowledge-based computation. A significant part of the course will involve presentations of research, both research papers and research done by students in their projects. Students interested in AI are strongly encouraged to select projects that will provide a basis for future AI research. Students not intending to focus on AI are encouraged to select projects that are relevant to their research interests in other areas.
There will be some homework, but the main part of the course will presentations and a semester research project involving developing a knowledge-based system and writing a paper on that research. This is expected to be a significant project going deeply into an area. For a some past students, this project has produced published conference papers and long-term research topics continuing beyond the class. Projects may be done individually or in teams of two students.
If you have to miss a class, you are still responsible for any readings and homeworks assigned there, so be sure to check with other students to find out what material you missed.
The programs that you write for assignments and the project should be designed to apply to a broad class of examples beyond those stated. This is described more completely in the on-line handout ``Guidelines for programming assignments.'' Please ask if you are unsure about the level of generality for a specifc portion of the code.
Programs should include a well-documented program and output demonstrating its processing. All homeworks should be handed in electronically before the class at which the assignment it is due, and a hardcopy is due in class. Unless otherwise specified, homeworks that are late will accepted up to two days late at a penalty of 10% per day late. After a 1-day grace period, final projects will be accepted up to two days late at a penalty of 5% per day.
For each presentation, one or more students will be assigned as discussants. The discussants will make a brief presentation after the main presentation, giving their own ideas and responding to the points raised in the presentation. Each discussant will also submit a 1-page sheet of comments and suggestions on the presentation by e-mail within 24 hours of the presentation. These written comments will be read by the instructor and passed on to the presenters.
During the semester, students will also be required to prepare brief progress reports on their projects. At the end of the course, each project group will present a longer presentation of their results.
Homework will count 20%, in-class presentations and commentaries as discussants will count 30%, and the final project (including presentations and written materials) will count 50%. For group work, team members may be asked to provide a course-grained assessment of the team members' relative contributions. It is expected that different members may make different types of contributions, but overall contributions are expected to be equivalent, for each team member to receive the same project score. If the instructor determines that there were significantly different levels of contribution, relative contributions may be used to weight final grades.
Incompletes will be handled in accordance with Computer Science Department policy. In particular, incompletes will only be given to students who have successfully completed most of the coursework, and who have an acceptable reason for the incomplete. Unexpected difficulty with other classes is not an acceptable reason for an incomplete.
Students are also encouraged to use the newsgroup to post notices of general AI interest and to discuss any questions and issues from AI and Cognitive Science.
The home page at URL http://www.cs.indiana.edu/classes/b552/index.html (also accessible from the CS home page at http://www.cs.indiana.edu) can be used to access this handout and other policy statements for the class, the class syllabus, lists of useful references, etc. Copies of each new assignment and other materials will be added as the semester progresses.
Students who need any special accommodation must contact the professor during the first week of class to discuss arrangements.
The Computer Science department has prepared a statement on academic integrity describing the obligations of students, a copy of which is accessible from the class web page. All students must read it before beginning the first homework assignment. All work must be done independently unless collaboration is explicitly allowed, and all collaboration must be properly acknowledged. Students are responsible for asking us if they have any questions about the policies stated here and in the departmental handout.
Students are asked not to do e-mail or other computer work in class.
If you have any questions that this doesn't cover, please let me know!
January 6, 2008.