Paper Info
Title
Piecewise-linear division of region by neural networks with maximum detectors
Abstract
A neural network with maximum detectors divides a space which has n-dimensions R(n) into piecewise-linear regions. However, there have been very limited theoretical researches concerning what kind of piecewise-linear region divisions can be realized by a neural network, that is, concerning the formation capability of piecewise-linear discriminate regions by a neural network. In this paper, this problem is considered theoretically. The concept of a individual region is introduced and then it is proved that a division can be realized by a piecewise-linear machine if and only if it is k-dividual.
Year
DOI
Venue
1994
10.1002/scj.4690250608
SYSTEMS AND COMPUTERS IN JAPAN
Keywords
DocType
Volume
MULTILAYER NEURAL NETWORK,PIECEWISE-LINEAR DIVISION,K-DIVIDUAL REGION,LAGUERRE-VORONOI DIVISION
Journal
25
Issue
ISSN
Citations 
6
0882-1666
0
PageRank 
References 
Authors
0.34
3
2
Name
Order
Citations
PageRank
Jian Zhuang110415.09
shunichi amari259921269.68