Open Access System for Information Sharing

Login Library

 

Article
Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Solving hard local minima problems using basin cells for multilayer Perceptron training SCIE SCOPUS

Title
Solving hard local minima problems using basin cells for multilayer Perceptron training
Authors
Yoon, YGLee, J
Date Issued
2005-01
Publisher
SPRINGER-VERLAG BERLIN
Abstract
An analysis of basin cells for an error surface of an multilayer perceptron is presented. Utilizing the topological structure of the basin cells, an escaping strategy is proposed to solve difficult local minima problems. A numerical example is given to illustrate the proposed method and is shown to have a potential to locate better local minima efficiently.
Keywords
UNSTABLE EQUILIBRIUM-POINT; STABILITY REGION ESTIMATE
URI
https://oasis.postech.ac.kr/handle/2014.oak/24517
DOI
10.1007/11427391_95
ISSN
0302-9743
Article Type
Article
Citation
LECTURE NOTES IN COMPUTER SCIENCE, vol. 3496, page. 597 - 602, 2005-01
Files in This Item:
There are no files associated with this item.

qr_code

  • mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher

이재욱LEE, JAEWOOK
Dept of Industrial & Management Enginrg
Read more

Views & Downloads

Browse