Your browser doesn't support javascript.
loading
Classification ability of single hidden layer feedforward neural networks.
Huang, G B; Chen, Y Q; Babri, H A.
Afiliação
  • Huang GB; School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore.
IEEE Trans Neural Netw ; 11(3): 799-801, 2000.
Article em En | MEDLINE | ID: mdl-18249806
Multilayer perceptrons with hard-limiting (signum) activation functions can form complex decision regions. It is well known that a three-layer perceptron (two hidden layers) can form arbitrary disjoint decision regions and a two-layer perceptron (one hidden layer) can form single convex decision regions. This paper further proves that single hidden layer feedforward neural networks (SLFN's) with any continuous bounded nonconstant activation function or any arbitrary bounded (continuous or not continuous) activation function which has unequal limits at infinities (not just perceptrons) can form disjoint decision regions with arbitrary shapes in multidimensional cases. SLFN's with some unbounded activation function can also form disjoint decision regions with arbitrary shapes.

Texto completo: 1 Base de dados: MEDLINE Idioma: En Ano de publicação: 2000 Tipo de documento: Article

Texto completo: 1 Base de dados: MEDLINE Idioma: En Ano de publicação: 2000 Tipo de documento: Article