Parallel implementation of a learning algorithm for multilayer perceptrons using transputers


Autoria(s): Ruano, A. E.; Jones, D. I.; Fleming, P. J.
Data(s)

11/02/2013

11/02/2013

1992

28/01/2013

Identificador

Ruano, A. E.; Jones, D. I; Fleming, P. J. Parallel Implementation of a Learning Algorithm for Multilayer Perceptrons using Transputers, Trabalho apresentado em Parallel Computing and Transputer Applications, In Parallel Computing and Transputer Applications, Barcelona, 1992.

AUT: ARU00698;

http://hdl.handle.net/10400.1/2278

Idioma(s)

eng

Direitos

restrictedAccess

Tipo

conferenceObject

Resumo

In this paper the parallelization of a new learning algorithm for multilayer perceptrons, specifically targeted for nonlinear function approximation purposes, is discussed. Each major step of the algorithm is parallelized, a special emphasis being put in the most computationally intensive task, a least-squares solution of linear systems of equations.