Attractor-based trust-region algorithm for efficient training of multilayer perceptrons
SCIE
SCOPUS
- Title
- Attractor-based trust-region algorithm for efficient training of multilayer perceptrons
- Authors
- Lee, J
- Date Issued
- 2003-05-01
- Publisher
- IEE-INST ELEC ENG
- Abstract
- A new training algorithm for multilayer perceptions is proposed. The first phase is a trust region-based local search for fast training of networks. The second phase is an attractor-based global search for escaping local minima. Benchmark results show that the proposed algorithm outperforms previously reported existing techniques.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/18532
- DOI
- 10.1049/EL:20030498
- ISSN
- 0013-5194
- Article Type
- Article
- Citation
- ELECTRONICS LETTERS, vol. 39, no. 9, page. 727 - 728, 2003-05-01
- 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.