Best approximation by Heaviside perceptron networks.

Kainen, P; Kůrková, V; Vogt, A · Neural Netw · 2000

other · Level V

Where this comes from

Abstract

In Lp-spaces with p an integer from [1, infinity) there exists a best approximation mapping to the set of functions computable by Heaviside perceptron networks with n hidden units; however for p an integer from (1, infinity) such best approximation is not unique and cannot be continuous.

Medical subject headings