Approximation by random networks with bounded number of layers

Author

Gelenbe, Erol ; Mao, Zhi-Hong ; Li, Yan-Da

Author_Institution

Dept. of Comput. Sci., Univ. of Central Florida, Orlando, FL, USA

fYear

1999

fDate

36373

Firstpage

166

Lastpage

175

Abstract

This paper discusses the function approximation properties of the Gelenbe random neural network (GNN). We use an extension of the basic model: the bipolar GNN (BGNN). We limit the networks to being feedforward and consider the case where the number of hidden layers does not exceed the number of input layers. We show that the feedforward BGNN with s hidden layers (total of s+2 layers) can uniformly approximate continuous functions of s variables

Keywords

feedforward neural nets; function approximation; learning (artificial intelligence); Gelenbe random neural network; bipolar neural network; continuous functions; hidden layers; input layers; Automation; Biological neural networks; Biological system modeling; Computer science; Function approximation; Mathematical model; Neural networks; Neurons; Polynomials; Recurrent neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks for Signal Processing IX, 1999. Proceedings of the 1999 IEEE Signal Processing Society Workshop.

Conference_Location

Madison, WI

Print_ISBN

0-7803-5673-X

Type

conf

DOI

10.1109/NNSP.1999.788135

Filename

788135

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3099777