This article is cited in 1 paper

Large Systems

Estimation of the Approximation Accuracy by Means of Superposition of Potential Functions

A. A. Pervozvanskii


Abstract: Estimates of the number of elements of an artificial neural network based on using elements of the potential-function type are given. It is shown that, under a reasonable choice of characteristics of the elements and not too large a dimension of space, the attainable approximation accuracy of smooth functions is not worse than that for sigmoidal-type perceptrons, while the adjustment is accomplished by a single parameter.

UDC: 621.391.1

Received: 20.06.1995

 English version: Problems of Information Transmission, 1996, 32:4, 331–341

Bibliographic databases:

• 
•