CS 281B/ Stat 241B: Advanced Topics in Machine Learning and Decision Making, Spring 2013

Lecture location and timing:  MW 4-5:30PM, 3111 ETCHEVERY

Instructor: Elchanan Mossel (mossel@stat dot berkeley dot edu)
Office hours: M 10:10-11:00, 401 EVANS

GSI: Joe Neeman

Office hours: TBA

The course will cover a number of topics in learning and decision making including:

1. An intro to geometry and probability in high dimensions.
2. Learning and VC dimension.
3. Singular Value Decomposition.
4. Algorithms for streams and big matrices.
5. Clustering.
6. Combinatorial Statistics. 
6. A selection of other topics. 


A draft of the new book "Computer Science Theory for the Information Age" by John Hopcroft and Ravi Kannan.
The draft is availible via BSPACE.

Links to other online resources will be posted later.

Online Resources:

Piazza (for questions and discussions; the site will be active at the beginning of the semester)

BSPACE (for homework problem sets and submissions; the site will be active and the beginning of the semester)


1. Final Project / Exam: 40%
2. Theoretical homework: 30%
3. Programing homework: 20%
4. Quizzes: 10%
5. Bonus points: Bonus points will be given for scribing (up to 5% per lecture), and finding typos and errors in the text-book. 

Please take the time to write clear and concise solutions; we will not grade messy or unreadable solutions. No late homework will be accepted.   

Collaboration and online resources:

You are encouraged to work on homework problems in study groups of two to four people; however, you must write up the solutions on your own, and you must never read or copy the solutions of other students. For each homework you must write your group member names and SID. Similarly, you may use books or online resources to help solve homework problems, but you must credit all such sources in your writeup and you must never copy material verbatim. Warning: Your attention is drawn to the Department's Policy on Academic Dishonesty. In particular, you should be aware that copying solutions, in whole or in part, from other students in the class or any other source without acknowledgment constitutes cheating. Any student found to be cheating risks automatically failing the class and being referred to the Office of Student Conduct.




Department of Statistics

Elchanan Mossel's homepage