Machine Learning and Data Mining

1. March 23: Sushil J. Louis, Hybrid Learning Using Genetic Algorithms and Decision Trees for Pattern Classification.

2. March 30: Ali Etezadi, Lazy decision Trees

3. April 1: Liyan Zhang, Effective Data Mining Using Neural Networks

4. April 6: Roman Zimmerman: Learning Rules that Classify E-Mail William W. Cohen.

5. April 8: Adam Nuzloch: Personal WebWatcher: Implementation and Design

6. April 13: Luchun Liao: Statistical Themes and Lessons for Data Mining.

7. April 15: Adam Altman: Fast Algorithms for Mining Association Rules in Large Databases

Here is the order in which each group will attack problems.

1. Adam and Roman: Cujo, Eng, LLNL
2. Adam and Ali: Eng, LLNL, Cujo
3. Liyan and Lu Chun: LLNL, Cujo, Eng

Rest of the Semester

• April 22: Initial results on one of our three problems. Each group will make a short 15 minute presentation and lead a 10 minute discussion on their problem, approach, and preliminary results. You will need to talk to me on the 16th or 19th about your results and plans for leading discussion.
• April 27: Medium term results on the next assigned problems. I expect to see improvements on each of the problems relative to the results on April 22. Presentation and discussion by each group as on the 22nd.
• April 29: What do you plan to do to get good results on all problems? Ideas, hypotheses, and final plan of attack. Layout of the final report.
• May 4: Presentation on Interactive Genetic Algorithms.
• May 12: Final Report DUE in my mailbox by 5:00 p.m. Spelling mistakes that spell checkers should catch will cost you 5% for each error. 10 spelling errors will destroy your grade.