Rüger, Stefan (1998). A Class of Asymptotically Stable Algorithms for Learning-Rate Adaptation. Algorithmica, 22(1-2), pp. 198–210.
| DOI (Digital Object Identifier) Link: | http://dx.doi.org/doi:10.1007/PL00013830 |
|---|---|
| Google Scholar | Look up in Google Scholar |
Abstract
A stability criterion for learning is given. In the case of learning-rate adaptation of backpropagation, a class of asymptotically stable algorithms is presented and studied, including a convergence proof. Simulations demonstrate relevance and limitations.
| Item Type: | Article |
|---|---|
| ISSN: | 0178-4617 |
| Academic Unit/Department: | Knowledge Media Institute |
| Item ID: | 11955 |
| Depositing User: | Rachel Barnett |
| Date Deposited: | 08 Oct 2008 14:13 |
| Last Modified: | 04 Apr 2011 10:23 |
| URI: | http://oro.open.ac.uk/id/eprint/11955 |
| Repository Staff Only: edit this item | |
| Public: Report issue/request change | |