Neural networks for function approximation

Author

Mhaskar, H.N. ; Khachikyan, L.

Author_Institution

Dept. of Math., California State Univ., Los Angeles, CA, USA

fYear

1995

fDate

31 Aug-2 Sep 1995

Firstpage

21

Lastpage

29

Abstract

We describe certain results of Mhaskar concerning the approximation capabilities of neural networks with one hidden layer. In particular, these results demonstrate the construction of neural networks evaluating a squashing function or a radial basis function for optimal approximation of the Sobolev spaces. We also report on the application of some of these ideas in the construction of general-purpose networks for the prediction of time series, when the number of independent variables is known in advance, such as the Mackey-Glass series or the flour data

Keywords

function approximation; neural nets; optimisation; Mackey-Glass series; Sobolev spaces; flour data; function approximation; neural networks; optimal approximation; radial basis function; squashing function; time series prediction; Algorithm design and analysis; Biological neural networks; Function approximation; Glass; Mathematics; Neural networks; Neurons; Sampling methods; Size measurement; Terminology;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks for Signal Processing [1995] V. Proceedings of the 1995 IEEE Workshop

Conference_Location

Cambridge, MA

Print_ISBN

0-7803-2739-X

Type

conf

DOI

10.1109/NNSP.1995.514875

Filename

514875