Instructor: Doug Downey
Office Hours: Fridays, 2:00-3:00 (or by appt), Ford 3-345
Teaching Assistant: Francisco Iacobelli
Office Hours: 2:00PM-3:00PM Tu., Ford 2-202
Submit your homework via email to f-iacobelli@northwestern.edu. Put EECS349-PS<problem set number>-<first name>-<LastName> on the subject of your email and attach a compressed ZIP file with the solution. The ZIP file naming convention is: PS<problem set number>-<first name>-<LastName>.zip. For example, if your name is James Bond and you are submitting your solution to Problem Set 1, you will send the TA an email with EECS349-PS1-James-Bond as the subject and you will attach the file PS1-James-Bond.zip which contains all the files that comprise your solution to Problem Set 1.
Problem Set 1 | Due 5:00PM Thursday, October 9 |
Problem Set 2 | Due 5:00PM Thursday, October 23 |
Problem Set 3 | Due 5:00PM Friday, November 7 |
Course projects will be performed in groups of 2 to 3 students. Your assignment is to formulate an interesting task for which machine learning can be used, gather training and test data for the task, and then evaluate one or more machine learning algorithms on the data. A final report (in ACM Proceedings format) of about 4 pages, and Web page due at the end of the quarter will summarize your results. For examples of past projects, see the previous years' project page. Groups are free to choose the topic of their choice; a number of potential project ideas will be discussed in class.
E-mail your project proposal (in RTF, text, pdf, or .doc format) to f-iacobelli@northwestern.edu and ddowney@eecs.northwestern.edu by 5:00PM October 16th. Please use the subject line "EECS 349 Project Proposal."
E-mail your final project report to f-iacobelli@northwestern.edu and ddowney@eecs.northwestern.edu by 11:59PM December 8th. Please use the subject line "EECS 349 Project Report." In the message, include a link to your project Web page.
Deadlines:
Project proposal | Due 5:00PM Thursday, October 16 (via e-mail; see above) |
Project report and Web page | Due 5:00PM Monday, December 8 |
Week of September 22 | Ch. 1 & 2 of Mitchell Wired data-mining article |
Week of September 29 | Ch. 3 of Mitchell |
Week of October 6 | Ch. 4 of Mitchell |
Week of October 13 | Ch. 10 of Mitchell, Ch. 5 of Mitchell |
Week of October 20 | Ch. 6 of Mitchell |
Week of October 27 | Ch. 8 of Mitchell |
Week of November 3 | Ch. 7 of Mitchell A Tutorial on Support Vector Machines for Pattern Recognition |
Week of November 10 | Ch. 9 of Mitchell |
Week of November 17 |
Tutorial on Hidden Markov Models
|
Week of December 1 | Ch. 13 of Mitchell
|
Week of September 22 | Introduction (adapted from P. Domingos, CSE 546 at U. of Washington) Version Spaces (adapted from B. Pardo, EECS 349) HW notes and project suggestions |
Week of September 29 | Decision Trees (from P. Domingos, CSE 546 at U. of Washington) |
Week of October 6 | Local Search (adapted from B. Pardo, EECS 349) Neural Networks (adapted from B. Pardo, EECS 349, and several others (see slides)) |
Week of October 13 | Notes on project grading, homework, etc. Rule Learning (adapted from P. Domingos, CSE 546 at U. of Washington) |
Week of October 13 | Bayesian Learning (adapted from B. Pardo, EECS 349) Hypothesis Testing (adapted from T. Mitchell, Machine Learning lecture notes) |
Week of October 20 | Bayesian Learning (adapted from B. Pardo, EECS 349) |
Week of October 27 | Instance-based Learning (adapted from P. Domingos, CSE 546 at U. of Washington) |
Week of November 3 |
Computational Learning Theory (adapted from B. Pardo, EECS 349) SVMs (some slides from Martin Law, Michigan State University) Clustering (adapted from B. Pardo, EECS 349, and P. Domingos, CSE 546 at U. of Washington) |
Week of November 10 |
Genetic Algorithms (adapted from B. Pardo, EECS 349) |
Week of November 17 |
Genetic Programming (adapted from B. Pardo, EECS 349) Hidden Markov Models (adapted from B. Pardo, EECS 349) |
Week of November 24 |
Notes on homework grading |
Week of December 1 |
Reinforcement Learning (adapted from B. Pardo, EECS 349, also Bill Smart, WashU St. Louis) Active Learning and re-cap |