Machine Learning

Spring 2004, CMSC 726
Course Links
Home
Announcements
Class Topics
Course Material
Project Information
Assignments
Contact Information
Related Links
ICML 2003
IEEE Explore
Weka
ACM SIGIR
ACM SIGKDD
Kurt Thearling's list of books
Beginner's guide to Matlab
Matlab Tutorial

 

Machine Learning, Spring 2004

Course Description:

Prerequisite: CMSC 421 or equivalent or permission of instructor. Covers both statistical machine learning and traditional symbolic machine learning. Topics include: supervised learning with discriminitive models (linear models, decision trees, nearest neighbor, SVMs); supervised and unsupervised learning with generative models (graphical models such as Bayesian networks); and learning theory (VC dimension, bias/variance tradeoff, PAC models). More complex models for sequence data (HMMs, CRFs) and graph data (MRFs, SCFGs) will be covered as time permits.


Final exam:

Tuesday May 18, 1:30-3:30 pm (one double sided page of handwritten notes allowed).



Time and Place:

Tuesday\Thursday: 12:30pm- 1:45pm (CSI 2120)


Mailing list: cmsc726@cs.umd.edu

To subscribe to the mailing list go to user's mailing list and fill out the form.

Grading Policy

Web Accessibility