Classic methods of Machine Learning
STAT 592 / CSE 590 MM Winter Quarter 2004



Books, software and other resources

Class mailing list



Course notes and reading

UW Statistics

UW Computer Science

Possible projects

A preliminary list of mini-projects: You can either choose one of the projects in this (still growing) list and do an experimental project, or, you can choose one of the papers in the additional reading list (see the Handouts page) and do a paper presentation. Project presentation will take place in the last 2 lectures of the quarters.
  • SVM and noise
  • Boosting and noise
  • Comparison Maximum Entropy Discrimination vs SVM
  • Comparison Generative vs Discriminative models
  • Does dimension reduction work for classification?
  • Finite and infinite mixtures as density estimators for small data sets
  • Maximum entropy models vs string kernels for text / biological sequences
  • Document clustering and topic discovery through Gaussian mixtures and Dirichlet processes
  • Speech recognition (or Isolated Word Recognition) with Gaussian mixtures
  • Comparing different "flavors" of boosting