CMPS 242, Machine Learning, Fall 2003

This course is about formalizing the "learning problem" and finding good algorithmic
solutions to various learning problems.

Project Deadline Announcement:

Several students have requested a deadline extension for the project report. The on-time deadline for the project report is 4:00pm Friday December 5.
In addition, students may turn in the project late. The late deadline is noon Monday December 8. Late project reports will be penalized 5%.

We now have a new room. Starting Thursday we will meet in Social Sciences II room 165. This room should be large enough to handle auditors. Any students needing a permission code to enroll should send me e-mail.

Instructor:

Prof. David Helmbold dph@cse.ucsc.edu

Office: 319 Applied Sciences

Office Hours: 4:00-4:45 Tu-Th

Lecture times:

Tu-Th 2-3:45 in Soc Sci II room 165 (new room).

Text:

Machine Learning by Mitchell.

Syllabus:

( Postscript )

( PDF )

Papers to read, pointers, etc.:

• Nick Littlestone's on-line learning/Winnow paper ( "Learning Quickly When ..." )
  
• Avrim Blum's "on-line learning survey" (also at http://www-2.cs.cmu.edu/~avrim/surveys.html
  and appearing as Chapter 14 in Online Algorithms: the State of the Art,
  Springer LNCS State-of-the-Art Survey" series 1442, Fiat and Woeginger eds.)
  
• Rob Schapire's boosting introduction: ( "The boosting approach to Machine Learning" ) (Also at http://www.cs.princeton.edu/~schapire/boost.html, and in
  MSRI Workshop on Nonlinear Estimation and Classification, 2002)
  
• The " Decision tree learning" AIexploratorium web site, ( http://www.aaai.org/Pathfinder/html/trees.html )
  
• The home page for Computational Learning Theory ( http://www.learningtheory.org/ )
  
• ICML 2003 papers ( www.hpl.hp.com/conferences/icml03/titlesAndAuthors.html )
  
• Tom Dietterich's "Machine Learning Research: Four Current Directions" ( postscript )

Handouts:

01: Course Information ( postscript ) ( pdf )

02: Homework 1: ( postscript ) ( pdf )

03: Solutions 1: ( postscript ) ( pdf )

04: Homework 2: ( postscript ) ( pdf )

05: A note on EM's derivation ( postscript ) ( pdf )

06: Homework 3: ( postscript ) ( pdf )

07: Solutions 2: ( postscript ) ( pdf )

08: Midterm review sheet ( postscript ) ( pdf )

09: Solutions 3: ( postscript ) ( pdf )

10: Score distribution ( text note )

Back to the CE / CS Class Home Pages.
Back to the CE / CS Home Page.