Title

Approximation with spiked random networks

Abstract

We examine the function approximation properties of the `random neural network model' (Gelenbe 89,90,93) [5, 6, 10]) or GNN. We consider a feedforward Bipolar GNN (BGNN) model (Gelenbe, Stafylopatis and Likas 91 [7]) which has both `positive (excitatory) and negative (inhibitory) neurons' in the output layer, and prove that the BGNN is a universal function approximator. Specifically, for any f∈C([0, 1]s) and any ε>0, we show that there exists a feedforward BGNN which approximates f uniformly with error less than ε. We also show that after a clamping operation on its output, the feedforward GNN is a universal continuous function approximator.

Publication Date

12-1-1998

Publication Title

Proceedings of the IEEE Conference on Decision and Control

Volume

1

Number of Pages

523-528

Document Type

Article

Personal Identifier

scopus

Socpus ID

0032273962 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/0032273962

This document is currently not available here.

Share

COinS