1.
IEEE Trans Neural Netw
; 4(5): 778-87, 1993.
Artigo
em Inglês
| MEDLINE
| ID: mdl-18276507
RESUMO
A novel approach is proposed which determines the number of layers, the number of neurons in each layer, and their connection weights for a particular implementation of a neural network, with the multilayer feedforward topology, designed to classify patterns in the multidimensional feature space. The approach is based on construction of a Voronoi diagram over the set of points representing patterns in feature space and this finds added usefulness in deriving alternate neural network structures for realizing the desired pattern classification.