Synthesis of feedforward networks in supremum error bound

Author

Ciesielski, Krzysztof ; Sacha, Jaroslaw P. ; Cios, Krzysztof J.

Author_Institution

Dept. of Math., West Virginia Univ., Morgantown, WV, USA

Volume

11

Issue

6

fYear

2000

fDate

11/1/2000 12:00:00 AM

Firstpage

1213

Lastpage

1227

Abstract

The main result of this paper is a constructive proof of a formula for the upper bound of the approximation error in L_∞ (supremum norm) of multidimensional functions by feedforward networks with one hidden layer of sigmoidal units and a linear output. This result is applied to formulate a new method of neural-network synthesis. The result can also be used to estimate complexity of the maximum-error network and/or to initialize that network´s weights. An example of the network synthesis is given.

Keywords

computational complexity; feedforward neural nets; multilayer perceptrons; L_∞ norm; approximation error upper bound; complexity estimation; feedforward network synthesis; linear output; maximum-error network; multidimensional functions; network weight initialization; neural-network synthesis; sigmoidal units; supremum error bound; supremum norm; Approximation error; Artificial neural networks; Indium tin oxide; Intelligent networks; Minimization methods; Multidimensional systems; Network synthesis; Network topology; Neurons; Upper bound;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.883398

Filename

883398