Hybrid back-propagation/genetic algorithm for multilayer feedforward neural networks

Author

Lu, Chun ; Shi, Bingxue

Author_Institution

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

Volume

1

fYear

2000

fDate

2000

Firstpage

571

Abstract

The BP (back-propagation algorithm) and GA (genetic algorithm) are among the most effective algorithms of neural networks (NN). As a deterministic gradient-descent algorithm and a stochastic optimizing algorithm respectively, there exits great compensability between their advantages and disadvantages. The proposed hybrid BP/GA learning method for a multilayer feedforward net blends the merits of both the 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

backpropagation; feedforward neural nets; genetic algorithms; search problems; HSPICE simulation results; VLSI; XOR problem solution; deterministic gradient-descent algorithm; genetic algorithm; hybrid BP/GA learning method; hybrid backpropagation/genetic algorithm; multilayer feedforward neural networks; search method; stochastic optimizing algorithm; two-layer feedforward neural 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

Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on

Conference_Location

Beijing

Print_ISBN

0-7803-5747-7

Type

conf

DOI

10.1109/ICOSP.2000.894556

Filename

894556