Artificial neural networks implementation on vectorial supercomputers

Author

Sánchez, E. ; Barro, S. ; Regueiro, C.V.

Author_Institution

Departamento de Electron. y Computacion, Santiago de Compostela Univ., Spain

Volume

6

fYear

1994

fDate

27 Jun- 2 Jul 1994

Firstpage

3938

Abstract

We present the results from the implementation of a multilayer perceptron with the backpropagation algorithm on a FUJITSU VP-2400/10 vectorial supercomputer. The programming methodology employed, tries to obtain the maximum performance in this kind of machines based on: input/output structures, treatment of conditional statements, do-loops vectorization and compiler directives. In this work, computing times for the VU (vectorial unit) and CPU are presented. These times indicate the possibility of real time operation in applications which demand artificial neural networks with a high structural complexity

Keywords

backpropagation; multilayer perceptrons; multiprocessing systems; parallel machines; vector processor systems; virtual machines; FUJITSU VP-2400/10 vectorial supercomputer; artificial neural networks; backpropagation algorithm; compiler directives; conditional statement treatment; do-loops vectorization; input/output structures; maximum performance; multilayer perceptron; structural complexity; Artificial neural networks; Backpropagation algorithms; Computer networks; Equations; Multilayer perceptrons; Neurons; Nonhomogeneous media; Speech recognition; Supercomputers; Very large scale integration;

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.1994.374841

Filename

374841