Class lectures: Mondays and Wednesdays 10:30-11:50 in Newell Simon Hall 1305
Recitations: Wednesday, 6:00-8:00 pm GHC 8102
Homework 5 is due on Wed, Dec 2nd.
Fri, Dec. 4, 1-4pm GHC 7th floor (under staircase)
Homework 4 solutions are posted
Machine Learning is concerned with computer programs that learn to make better predictions or take better actions given increasing numbers of observations (e.g., programs that learn to spot high-risk medical patients, recognize human faces, recommend music and movies, or drive autonomous robots). This course covers theory and practical algorithms for machine learning from a variety of perspectives. We cover topics such as Bayesian networks, boosting, support-vector machines, dimensionality reduction, and reinforcement learning. The course also covers theoretical concepts such as bias-variance trade-off, PAC learning, margin-based generalization bounds, and Occam's Razor. Short programming assignments include hands-on experiments with various learning algorithms. Typical assignments include learning to automatically classify email by topic, and learning to automatically classify the mental state of a person from brain image data. The course will include a term project where the students will have opportunity to explore some of the class topics on a real-world data set in more detail.
Students entering the class with a pre-existing working knowledge of probability, statistics and algorithms will be at an advantage, but the class has been designed so that anyone with a strong numerate background can catch up and fully participate. This class is intended for Masters students and advanced undergraduates.
Announcement Emails
- Class announcements will be broadcasted using a group email list:
- If you are registered for the course, you have automatically been added to the mail group. If you are for some reason NOT receiving these announcements, you can subscribe via the 10601-09f-announce list page.
- For changes (incl. additions or removal) to your membership in the course list, please make changes directly via the list administration page.
Textbooks
- Textbook: Pattern Recognition and Machine Learning , Chris Bishop.
Grading
- Class Participation (5%)
- Homeworks (4-5 assignments 40%)
- Midterm exam (Wed Nov 2, 2009 in room NSH 1305) (30%)
- Final project (25%)
Auditing
- If you are a graduate student, and you don't want to take the class for credit, you must register to audit the class. If you want, you can hande in HWs or partial HWs for feedback if desired. Make sure to mark your HWs "audit".
- If you are not a student and want to sit in the class, you don't need to officially audit.
Homework policy
Important Note: As we sometimes reuse problem set questions from previous years, or problems covered by papers and web pages, we expect the students will not copy, refer to, or look at the solutions in preparing their answers. Since this is an upper level course, we hope you want to learn and not Google for answers. The purpose of problem sets is to help you think about the material, not just give us the right answers. Therefore, please restrict attention to the books mentioned on the web page when solving problem sets. If you do happen to use other material, acknowledge it clearly with a citation on the submitted solution.
Collaboration policy
Homeworks will be done individually: each student must hand in their own answers. In addition, each student must write their own code in the programming part of the assignment. It is acceptable, however, for students to collaborate on general solution strategies. We assume that, as participants of an upper level course, you will be taking the responsibility to make sure you personally understand the solution to any work arising from such collaboration. To help ensure that you understand every solution, you may take notes during study sessions, but in preparing your own writeup, you must close your notes and not refer to any written materials from a joint study session. Indicate on each homework with whom you collaborated. The final project may be completed in teams of 2-3 students.Late homework policy
- Homeworks are due at the beginning of class, unless otherwise specified
- You will be allowed 5 total late days without penalty for the entire semester, which you may distribute among your assignments however you wish. Each late day corresponds to 24 hours or part thereof.
- Indicate at the top of each homework how many late days you are applying (otherwise we assume you are applying none). Beyond your applied late days, you will receive half credit for an additional 48 hours, provided you hand in your assignment within 5 days of the original due date.
- Homework is worth zero credit after the applied late days + 48 hours, or after five days from the original due date, whichever comes first.
- You must satisfactorily complete and turn in all of the 5 homework, even if for zero credit, in order to pass the course.
- All written assignments should be clearly organized and legible; we encourage people to typeset their assignments if they have any question about legibility. Some typesetting tools: Latex , Lyx , Mathematica.
- Turn in all late homework assignments to Michelle (Gates Center 8001) , or by e-mail as a single PDF file to both instructors and both TAs. The subject line of the late homework emails should be: "10601 Late Homework Submission Firstname Lastname and HW number". For this purpose, there are document scanners in many copy rooms which can turn paper solutions into PDFs (refer to SCS Facilities documentation for where).
Homework regrading policy
If you feel that we have made an error in grading your homework, please turn in your homework with a written explanation to Michelle, and we will consider your request. Please note that regrading of a homework may cause your grade to go up or down.Final project
The course project will account for the 25% of the final grade, the following will contribute to the project grade:
- Project proposal due date Wed, Sep 23 10:30 am (0% of project grade)
- Milestone 1 due date Wed, Oct 14 10:30 am(10% of project grade)
- Milestone 2 due date Wed, Nov 11 10:30 am (15% of project grade)
- Two-minute presentation of Milestone 2 results Mon, Nov 11 9:00 am via email (0% of project grade)
- Poster session date Fri, Dec. 4, 1-4pm GHC 7th floor (35% of project grade)
- Paper due date Fri, Dec. 11 10:30 am (40% of project grade)
For project milestone, roughly half of the project work should be completed. A short write-up will be required, and we will provide feedback.