Parallel back-propagation using genetic algorithm: real-time BP learning on the massively parallel computer CP-PACS

Author

Yasunaga, Moritoshi ; Yoshida, Eiji ; Yoshihara, Ikuo

Author_Institution

Inst. of Inf. Sci. & Electron., Tsukuba Univ., Ibaraki, Japan

Volume

6

fYear

1999

fDate

36342

Firstpage

4175

Abstract

In this paper, we propose a parallel backpropagation algorithm using the genetic algorithm to reduce the learning time to reach the optimal solution. Genetic algorithm is used in parallel previous to the parallel backpropagation regarding the set of weights in the feedforward neural network as chromosomes, and well-evolved chromosomes (sets of excellent initial weights) are used in the parallel backpropagation. Performance of the proposed algorithm was evaluated experimentally in 5-bit and 8-bit parity problems using the massively parallel computer CP-PACS. The learning speeds were about 3 times and about 7 times faster than those of the simple parallel backpropagation in the 5-bit and the 8-bit parity problems, respectively

Keywords

backpropagation; computational complexity; feedforward neural nets; genetic algorithms; parallel processing; real-time systems; 5-bit parity problems; 8-bit parity problems; GA; feedforward neural network; genetic algorithm; massively parallel computer CP-PACS; parallel back-propagation; parallel backpropagation algorithm; real-time BP learning; well-evolved chromosomes; Artificial neural networks; Biological cells; Chromosome mapping; Computer networks; Concurrent computing; Genetic algorithms; Iterative algorithms; Large-scale systems; Neural networks; Real time systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1999. IJCNN '99. International Joint Conference on

Conference_Location

Washington, DC

ISSN

1098-7576

Print_ISBN

0-7803-5529-6

Type

conf

DOI

10.1109/IJCNN.1999.830834

Filename

830834