Title
Approximation By Random Networks With Bounded Number Of Layers
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.
Publication Date
12-1-1999
Publication Title
Neural Networks for Signal Processing - Proceedings of the IEEE Workshop
Number of Pages
166-175
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
Copyright Status
Unknown
Socpus ID
0033312854 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/0033312854
STARS Citation
Gelenbe, Erol; Mao, Zhi Hong; and Li, Yan Da, "Approximation By Random Networks With Bounded Number Of Layers" (1999). Scopus Export 1990s. 4256.
https://stars.library.ucf.edu/scopus1990/4256