Scheduled System Maintenance:
Some services will be unavailable Sunday, March 29th through Monday, March 30th. We apologize for the inconvenience.
By Topic

On Descent Spectral CG Algorithms for Training Recurrent Neural Networks

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

The purchase and pricing options are temporarily unavailable. Please try again later.
3 Author(s)
Livieris, I.E. ; Dept. of Math., Univ. of Patras, Patras, Greece ; Sotiropoulos, D.G. ; Pintelas, P.

In this paper, we evaluate the performance of descent conjugate gradient methods and we propose a new algorithm for training recurrent neural networks. The presented algorithm preserves the advantages of classical conjugate gradient methods while simultaneously avoids the usually inefficient restarts. Simulation results are also presented using three different recurrent neural network architectures in a variety of benchmarks.

Published in:

Informatics, 2009. PCI '09. 13th Panhellenic Conference on

Date of Conference:

10-12 Sept. 2009