Journal of Chemical Software
Online ISSN : 1883-8359
Print ISSN : 0918-0761
ISSN-L : 0918-0761
Development of NEural network simulator for structureactivity COrrelation of molecules : Neco (3)
Performance Evaluation of Self-organized Network and Perceptron
Yasuko FUJITANIMitsue ONODERAYoshimi ISUUmpei NAGASHIMAHaruo HOSOYATomoo AOYAMA
Author information
JOURNALS FREE ACCESS

1998 Volume 4 Issue 1 Pages 19-32

Details
Abstract

A Self-organized network model for high-speed learning was included in the perceptron type Neural network simulator for structure-activity correlation of molecules : Neco. The performance of the Self-organized network model was compared with that of perceptron using twodimensional exclusive OR problem and the relationship between 13C-NMR shift and the conformation of norbornane. For practical use, the speed for convergence of the Self-organized network is almost four times faster than that of perceptron though perceptron gives higher order convergence. In the case of 13C-NMR shift and conformation of norbornane, a Self-organized network seems to show strong nonlinear classification in comparsion with perceptron.

Information related to the author
© Society of Computer Chemistry, Japan
Previous article Next article
feedback
Top