Hybrid BP-GA for multilayer feedforward neural networks

Author

Lu, Chun ; Shi, Bingxue ; Chen, Lu

Author_Institution

Inst. of Microelectron., Tsinghua Univ., Beijing, China

Volume

2

fYear

2000

fDate

2000

Firstpage

958

Abstract

BP (backpropagation algorithm) and GA (genetic algorithm) are among the most effective algorithms of neural networks (NN). As deterministic gradient-descent algorithm and stochastic optimizing algorithm respectively, there exists great compatibility between their advantages and disadvantages. The proposed hybrid BP-GA learning method for multilayer feedforward neural networks blends the merits of both BP and GA. Based on BP-GA, a two-layer feedforward neural network is designed. HSPICE simulation results have proved its ability to solve the XOR problem

Keywords

SPICE; backpropagation; deterministic algorithms; feedforward neural nets; genetic algorithms; gradient methods; multilayer perceptrons; HSPICE simulation; XOR problem; deterministic gradient-descent algorithm; hybrid BP-GA; multilayer feedforward neural networks; stochastic optimizing algorithm; two-layer network; Arithmetic; Convergence; Feedforward neural networks; Genetic algorithms; Hardware; Learning systems; Microelectronics; Multi-layer neural network; Neural networks; Stochastic processes;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronics, Circuits and Systems, 2000. ICECS 2000. The 7th IEEE International Conference on

Conference_Location

Jounieh

Print_ISBN

0-7803-6542-9

Type

conf

DOI

10.1109/ICECS.2000.913035

Filename

913035