Knowledge Discovery and Data-Mining - 1998

Course Topic breakdown

1. Introduction - overview of KDD
2. Visualization of databases
3. Association rule induction algorithms
4. Graphical probability models - reasoning and learning from data
5. Inductive logic programming
6. Decision tree induction
7. Database and data warehouse aspects of data-mining

In addition, hands-on exercises on an existing KDD system under development at the CS department will be offered.

Reading List

As this is a new field, few textbooks, if any, are in existence. Course material was prepared loosely from the following reading list, which also contains papers for student presentations.

• Advances in Knowledge Discovery and Data Mining, by Usama M. Fayyad, Gregory Piatetsky-Shapiro, Padhraic Smyth, and Ramasamy Uthurusamy, Eds. AAAI Press / The MIT Press, 1996.
• Proceedings of the conference on Knowledge Discovery in Databases, 1996, 1997.
• Tutorial slides from KDD 1997.

Prerequisites and Requirements

This course is primarily for graduate students, open to advanced undergraduate students who have already taken at least one related elective course, or otherwise by instructor's permission. Related electives are: artificial intelligence, computer graphics, databases, planning and decision-making, logic programming.

Grades in the course will be based on (roughly): 50% course project, 30% "attendance-check" quizzes, 10% course exercises, and 10% for a talk (or critical analysis) on a paper selected by the student from a list of related papers.

Back to BGU Math & CS HomePage