New parallel algorithms for back-propagation learning

Author

Alves, R.Lde.S. ; De Melo, Jorge D. ; Net, Adrião D Dória ; Albuquerque, Ana Claudia M L

Author_Institution

Departamento de Engenharia de Computacao e Automacao, Univ. Fed. do Rio Grande do Norte, Natal, Brazil

Volume

3

fYear

2002

fDate

6/24/1905 12:00:00 AM

Firstpage

2686

Lastpage

2691

Abstract

It is presented in this work new parallel algorithms to train a multilayer perceptron network using the error backpropagation algorithm. An analysis of the different paralleling strategies used is shown and aspects such as-task definition and communications profile were taken into account. An application in image compression illustrates the capacity of these new procedures when compared to the classical approach and to other parallel implementations

Keywords

backpropagation; multilayer perceptrons; parallel algorithms; back-propagation learning; communications profile; error backpropagation algorithm; image compression; multilayer perceptron network; parallel algorithms; paralleling strategies; task definition; Computer networks; Concurrent computing; Cost function; Image coding; Multilayer perceptrons; Neural networks; Neurons; Parallel algorithms; Parallel processing; Scalability;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on

Conference_Location

Honolulu, HI

ISSN

1098-7576

Print_ISBN

0-7803-7278-6

Type

conf

DOI

10.1109/IJCNN.2002.1007571

Filename

1007571