Goals of the course

[Info]Goals

Goals:

A learning machine is one that can adapt its behavior based on its past history and feedback from its environment. This class provides an introduction to the foundations, theory and practice of machine learning. 

Topics covered in class include:

Online learning
Bayesian inference
PAC learning
Non-parametric classification
VC theory
Linear separators
Support Vector Machines
Boosting
Unsupervised learning & clustering


Recommended Bibliography:

  • An Introduction to Computational Learning Theory
    by Michael J. Kearns, Umesh V. Vazirani, MIT Press

  • A Probabilistic Theory of Pattern Recognition
    by Luc Devroye, Laszlo Gyorfi, Gabor Lugosi, Springer

  • The Nature of Statistical Learning Theory
    by Vladimir Vapnik, Springer

  • Pattern Classification and Scene Analysis
    by Richard O. Duda, Peter E. Hart, Wiley

  • Neural Networks for Pattern Recognition
    by Christopher M. Bishop, Oxford Univ Press

  • Neural Network Learning: Theoretical Foundations,
    by Anthony and Bartlett, Cambridge University Press, 1999.


Links:


Go Back to the Course Page