Derivation of a class of training algorithms

1 June 1990

journal article
Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks

Vol. 1 (2) , 229-232
https://doi.org/10.1109/72.80234

Abstract

A novel derivation is presented of T. Kohonen's topographic mapping training algorithm (Self-Organization and Associative Memory, 1984), based upon an extension of the Linde-Buzo-Gray (LBG) algorithm for vector quantizer design. Thus a vector quantizer is designed by minimizing an L(2) reconstruction distortion measure, including an additional contribution from the effect of code noise which corrupts the output of the vector quantizer. The neighborhood updating scheme of Kohonen's topographic mapping training algorithm emerges as a special case of this code noise model. This formulation of Kohonen's algorithm is a specific instance of the robust hidden layer principle, which stabilizes the internal representations chosen by a network against anticipated noise or distortion processes.

Keywords

This publication has 9 references indexed in Scilit:

Image compression using a multilayer neural network
Pattern Recognition Letters, 1989
The Use of Bayesian and Entropic Methods in Neural Network Theory
Published by Springer Nature ,1989
Hierarchical vector quantisation
IEE Proceedings I Communications, Speech and Vision, 1989
Reducing transmission error effects using a self-organizing network
Published by Institute of Electrical and Electronics Engineers (IEEE) ,1989
Kohonen's self-organizing maps: exploring their computational capabilities
Published by Institute of Electrical and Electronics Engineers (IEEE) ,1988
Self-organising multilayer topographic mappings
Published by Institute of Electrical and Electronics Engineers (IEEE) ,1988
Least squares quantization in PCM
IEEE Transactions on Information Theory, 1982
An Algorithm for Vector Quantizer Design
IEEE Transactions on Communications, 1980
Quantizing for minimum distortion
IEEE Transactions on Information Theory, 1960