Peng, C.C. and Magoulas, George D. (2009) Nonmonotone learning of recurrent neural networks in symbolic sequence processing applications. pp. 325-335. ISSN 1865-0929.
Abstract
In this paper, we present a formulation of the learning problem that allows deterministic nonmonotone learning behaviour to be generated, i.e. the values of the error function are allowed to increase temporarily although learning behaviour is progressively improved. This is achieved by introducing a nonmonotone strategy on the error function values. We present four training algorithms which are equipped with nonmonotone strategy and investigate their performance in symbolic sequence processing problems. Experimental results show that introducing nonmonotone mechanism can improve traditional learning strategies and make them more effective in the sequence problems tested.
Metadata
| Item Type: | Article |
|---|---|
| Keyword(s) / Subject(s): | BFGS, conjugate gradient, Levenberg-Marquardt, nonmonotone learning, recurrent neural networks, resilient propagation, training algorithms, symbolic sequences |
| School: | Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences |
| Research Centres and Institutes: | Birkbeck Knowledge Lab |
| Depositing User: | Administrator |
| Date Deposited: | 05 Apr 2011 13:53 |
| Last Modified: | 09 Aug 2023 12:30 |
| URI: | https://eprints.bbk.ac.uk/id/eprint/3255 |
Statistics
Additional statistics are available via IRStats2.
Archive Staff Only (login required)
