Neural Computation
January 1993, Vol. 5, No. 1, Pages 132-139
(doi: 10.1162/neco.1993.5.1.132)
Generalization and Approximation Capabilities of Multilayer Networks
Article PDF (369.93 KB)
Abstract
This paper develops a theory for constructing 3-layered networks. The theory allows one to specify a finite discrete set of training data and a network structure (minimum intermediate units, synaptic weights and biases) that generalizes and approximates any given continuous mapping between sets of contours on a plane within any given permissible error.