Capabilities of three-layered perceptrons

1 January 1988

conference paper
Published by Institute of Electrical and Electronics Engineers (IEEE)

p. 641-648 vol.1
https://doi.org/10.1109/icnn.1988.23901

Abstract

A theorem is proved to the effect that three-layered perceptrons with an infinite number of computing units can represent arbitrary mapping if the desired mapping and the input-output characteristics of the computing units satisfy some constraints. The proof is constructive, and each coefficient is explicitly presented. The theorem theoretically guarantees a kind of universality for three-layered perceptrons. Although two-layered perceptrons (simple perceptrons) cannot represent arbitrary functions, three-layers prove necessary and sufficient. The relationship between the model used in the proof and the distributed storage and processing of information is also discussed.

Keywords

NEURAL NETWORKS

This publication has 5 references indexed in Scilit:

An introduction to computing with neural nets
IEEE ASSP Magazine, 1987
A mathematical model of the primary visual cortex and hypercolumn
Biological Cybernetics, 1986
Learning Internal Representations by Error Propagation
Published by Defense Technical Information Center (DTIC) ,1985
On the structure of continuous functions of several variables
Transactions of the American Mathematical Society, 1965
The perceptron: A probabilistic model for information storage and organization in the brain.
Psychological Review, 1958