A regularized line search tunneling for efficient neural network learning
SCIE
SCOPUS
- Title
- A regularized line search tunneling for efficient neural network learning
- Authors
- Lee, DW; Choi, HJ; Lee, J
- Date Issued
- 2004-01
- Publisher
- SPRINGER-VERLAG BERLIN
- Abstract
- A novel two phases training algorithm for a multilayer perceptron with regularization is proposed to solve a local minima problem for training networks and to enhance the generalization property of networks trained. The first phase is a trust region-based local search for fast training of networks. The second phase is an regularized line search tunneling for escaping local minima and moving toward a weight vector of next descent. These two phases are repeated alternatively in the weight space to achieve a goal training error. Benchmark results demonstrate a significant performance improvement of the proposed algorithm compared to other existing training algorithms.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/17747
- DOI
- 10.1007/978-3-540-28647-9_41
- ISSN
- 0302-9743
- Article Type
- Article
- Citation
- LECTURE NOTES IN COMPUTER SCIENCE, vol. 3173, page. 239 - 243, 2004-01
- 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.