A new method in neural network supervised training with imprecision
Magoulas, George and Vrahatis, M.N. and Androulakis, G.S. (1996) A new method in neural network supervised training with imprecision. In: UNSPECIFIED (ed.) Proceedings of Third International Conference on Electronics, Circuits, and Systems: ICECS 1996. IEEE Computer Society, pp. 287-290. ISBN 078033650X.
Abstract
We propose a method that proceeds solely with the minimal information of the error function and gradient which is their algebraic signs and takes minimization steps in each weight direction. This approach seems to be practically useful especially when training is affected by technology imperfections and environmental changes that cause unpredictable deviations of parameter values from the designed configuration. Therefore, it may be difficult or impossible to obtain very precise values for the error function and the gradient of error during training.
Metadata
Item Type: | Book Section |
---|---|
School: | Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences |
Depositing User: | Sarah Hall |
Date Deposited: | 06 Jul 2021 13:55 |
Last Modified: | 09 Aug 2023 12:51 |
URI: | https://eprints.bbk.ac.uk/id/eprint/45013 |
Statistics
Additional statistics are available via IRStats2.