Competitive learning with generalized winner-take-all activation

Author

Lemmon, Michael ; Kumar, B. V K Vijaya

Author_Institution

Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburg, PA, USA

Volume

3

Issue

2

fYear

1992

fDate

3/1/1992 12:00:00 AM

Firstpage

167

Lastpage

175

Abstract

Competitive learning paradigms are usually defined with winner-take-all (WTA) activation rules. The paper develops a mathematical model for competitive learning paradigms using a generalization of the WTA activation rule (g-WTA). The model is a partial differential equation (PDE) relating the time rate of change in the `density´ of weight vectors to the divergence of a vector field called the neural flux. Characteristic trajectories are used to study solutions of the PDE model over scalar weight spaces. These solutions show how the model can be used to design competitive learning algorithms which estimate the modes of unknown probability density functions

Keywords

learning systems; neural nets; partial differential equations; characteristic trajectories; competitive learning; divergence; generalized winner-take-all activation; neural flux; neural nets; partial differential equation; probability density functions; vector field; Algorithm design and analysis; Helium; Intelligent networks; Mathematical model; Military computing; Neurons; Partial differential equations; Probability density function; Stationary state; Vectors;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.125858

Filename

125858