Our goals are to learn something about machine learning techniques and to get a feel for the nature of artificial intelligence research.
We'll be looking at four fields in and around machine learning. The first two weeks will tend to emphasize techniques more, while the second two weeks will be more speculative.
| Session | Material |
| 1 | Data mining |
| 2 | : |
| 3 | Neural networks |
| 4 | : |
| 5 | Reinforcement learning |
| 6 | : |
| 7 | Artificial life |
| 8 | : |
Without question, the greatest resource at your disposal is the CS staff. We are employed full-time to help you learn about CS. Never hesitate to ask for help!
| Carl Burch | Machine learning instructor | |
| Todd Hierlmaier | TA | |
| Amy Ogan | TA | |
| Ethan Tira-Thompson | TA |
Feel free to talk with the instructor or the TAs about course material at any time, including during cluster hours intended for CS core.
I'm making it up as we go along. With luck, I'll be able to keep up and give you written notes for each week as we come to it.
There will also be some assigned reading of research papers for assignments.
Assignments are due at 1:30pm each Monday. I'll specify the extent of collaboration allowed on each assignment. When you may work in a group, you can submit only one solution per group.
The assignments will emphasize practice of techniques taught in class and comprehension of material. I intend to set nothing harsh, nothing burdensome - just enough to give you an opportunity to get a handle on things. There are a total of four assignments; none should take more than two hours. If you're finding otherwise, let me know!
None of the assignments will involve programming: There's plenty for us to study without implementing techniques, and few students have a deep enough programming knowledge to make it work anyway.
I reserve the right to administer pop quizzes or scheduled quizzes as I like. The primary motivation for this would be a general sense that several individuals aren't doing the homework due to abuse of the groupwork policy.
The course Web page is www.cburch.com/pgss/ml.