Title
On-Line Gauss-Newton-Based Learning For Fully Recurrent Neural Networks
Abstract
In this paper we propose a novel, Gauss-Newton-based variant of the Real Time Recurrent Learning (RTRL) algorithm by Williams and Zipser (Neural Comput. 1 (1989) 270-280) for on-line training of Fully Recurrent Neural Networks. The new approach stands as a robust and effective compromise between the original, gradient-based RTRL (low computational complexity, slow convergence) and Newton-based variants of RTRL (high computational complexity, fast convergence). By gathering information over time in order to form Gauss-Newton search vectors, the new learning algorithm, GN-RTRL, is capable of converging faster to a better quality solution than the original algorithm. Experimental results reflect these qualities of GN-RTRL, as well as the fact that GN-RTRL may have in practice lower computational cost in comparison, again, to the original RTRL. © 2005 Elsevier Ltd. All rights reserved.
Publication Date
11-30-2005
Publication Title
Nonlinear Analysis, Theory, Methods and Applications
Volume
63
Issue
5-7
Number of Pages
-
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1016/j.na.2005.02.015
Copyright Status
Unknown
Socpus ID
28044460611 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/28044460611
STARS Citation
Vartak, A. A.; Georgiopoulos, M.; and Anagnostopoulos, G. C., "On-Line Gauss-Newton-Based Learning For Fully Recurrent Neural Networks" (2005). Scopus Export 2000s. 3514.
https://stars.library.ucf.edu/scopus2000/3514