Generalization and Approximation Capabilities of Multilayer Networks
- 1 January 1993
- journal article
- research article
- Published by MIT Press in Neural Computation
- Vol. 5 (1) , 132-139
- https://doi.org/10.1162/neco.1993.5.1.132
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.This publication has 4 references indexed in Scilit:
- Generalizing Smoothness Constraints from Discrete SamplesNeural Computation, 1990
- Minimum class entropy: A maximum information approach to layered networksNeural Networks, 1989
- On the approximate realization of continuous mappings by neural networksNeural Networks, 1989
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989