Some Competitive Learning Methods

Bernd Fritzke
Systems Biophysics
Institute for Neural Computation
Ruhr-Universität Bochum
 
 Draft from April 5, 1997
 
(Some additions and refinements are planned for this document so it
will stay in the draft status still for a while.)
Comments are welcome.

 

Abstract:

This report has the purpose of describing several algorithms from the literature all related to competitive learning. A uniform terminology is used for all methods. Moreover, identical examples are provided to allow a qualitative comparisons of the methods. The complete Java source code as well as a postscript version of this document may be accessed by ftp.

 
• Contents
• Introduction
• Common Properties and Notational Conventions
• Goals of Competitive Learning
  • Error Minimization
  • Entropy Maximization
  • Feature Mapping
  • Other Goals
• Hard Competitive Learning
  • Batch Update: LBG
  • On-line Update: Basic Algorithm
  • Constant Learning Rate
  • k-means
  • Exponentially Decaying Learning Rate
• Soft Competitive Learning without Fixed Network Dimensionality
  • Neural Gas
  • Competitive Hebbian Learning
  • Neural Gas plus Competitive Hebbian Learning
  • Growing Neural Gas
  • Other Methods
• Soft Competitive Learning with Fixed Network Dimensionality
  • Self-organizing Feature Map
  • Growing Cell Structures
  • Growing Grid
  • Other Methods
• Quantitative Results (t.b.d.)
• Discussion (t.b.d.)
• References
• About this document ...