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