A Simulated Annealing-based Learning Algorithm for Block-Diagonal Recurrent Neural Networks
dc.conference.information | Innsbruck, Austria, February 13-16, 2006 | el |
dc.conference.name | Fifth IASTED International Conference on Artificial Intelligence and Applications | el |
dc.contributor.author | Mastorocostas, P. A. | |
dc.contributor.author | Varsamis, D. N. | |
dc.contributor.author | Mastorocostas, C. A. | |
dc.date.accessioned | 2015-06-29T16:28:58Z | |
dc.date.accessioned | 2024-09-27T18:12:19Z | |
dc.date.available | 2015-06-29T16:28:58Z | |
dc.date.available | 2024-09-27T18:12:19Z | |
dc.date.issued | 2006 | |
dc.description.abstract | The RPROP algorithm was originally developed in [5] for static networks and constitutes one of the best performing first order learning methods for neural networks [6]. However, in RPROP the problem of poor convergence to local minima, faced by all gradient descent-based methods, is not fully eliminated. Hence, in an attempt to alleviate this drawback, a combination of RPROP with the global search technique of Simulated Annealing (SA) was introduced in [7]. The resulted algorithm, named SARPROP, was proved to be an efficient learning method for static neural networks. A fast and efficient training method for block-diagonal recurrent fuzzy neural networks is proposed. The method modifies the Simulated Annealing RPROP algorithm, originally developed for static models, in order to be applied to dynamic systems. A comparative analysis with a series of algorithms and recurrent models is given, indicating the effectiveness of the proposed learning approach. | en |
dc.format.extent | 6 | el |
dc.identifier.other | http://www.actapress.com/PaperInfo.aspx?PaperID=23195&reason=500 | el |
dc.identifier.uri | https://repository2024.ihu.gr/handle/123456789/1559 | |
dc.language.iso | en | el |
dc.publication.category | Απαγόρευση δημοσίευσης - Βιβλιογραφική αναφορά | el |
dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 Διεθνές | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
dc.title | A Simulated Annealing-based Learning Algorithm for Block-Diagonal Recurrent Neural Networks | en |
dc.type | Άρθρο σε επιστημονικό συνέδριο | el |
Αρχεία
Φάκελος/Πακέτο αδειών
1 - 1 από 1
Δεν υπάρχει διαθέσιμη μικρογραφία
- Ονομα:
- license.txt
- Μέγεθος:
- 508 B
- Μορφότυπο:
- Plain Text
- Περιγραφή: