Parallel training of simple recurrent neural networks

Author

McCann, Peter J. ; Kalman, Barry L.

Author_Institution

Dept. of Comput. Sci., Washington Univ., St. Louis, MO, USA

Volume

1

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

167

Abstract

A concurrent implementation of the method of conjugate gradients for training Elman networks is discussed. The parallelism is obtained in the computation of the error gradient and the method is therefore applicable to any gradient descent training technique for this form of network. The experimental results were obtained on a Sun Sparc Center 2000 multicomputer. The Spare 2000 is a shared memory machine well suited to coarse-grained distributed computations, but the concurrency could be extended to other architectures as well

Keywords

learning (artificial intelligence); parallel processing; recurrent neural nets; shared memory systems; Elman networks; Sun Sparc Center 2000 multicomputer; coarse-grained distributed computations; conjugate gradients; error gradient; gradient descent training; parallel training; recurrent neural networks; shared memory machine; Computer architecture; Computer errors; Computer networks; Computer science; Concurrent computing; Distributed computing; Kalman filters; Neural networks; Recurrent neural networks; Sun;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374157

Filename

374157