A Method of Improved BP Neural Algorithm Based on Simulated Annealing Algorithm

This paper analyses the BP algorithm in detail, including the number of hidden layer, the amount of neural node and training algorithm. In order to improve the training speed, this paper adopts the automatic and adaptive step to perfect the BP algorithm. In addition, because the traditional BP neura...

Full description

Saved in:
Bibliographic Details
Published in2009 3rd International Conference on Genetic and Evolutionary Computing pp. 765 - 768
Main Authors Kai Bai, Jing Xiong
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2009
Subjects
Analytical models
Approximation algorithms
Artificial neural networks
Biological neural networks
Biological system modeling
BP Neural Algorithm
Computational modeling
Computer science
Computer simulation
Genetics
neural network
Simulated annealing
simulated annealing algorithm
Online AccessGet full text
ISBN9781424452453
1424452457
9780769538990
0769538991
DOI10.1109/WGEC.2009.39

Cover

More Information
Summary:This paper analyses the BP algorithm in detail, including the number of hidden layer, the amount of neural node and training algorithm. In order to improve the training speed, this paper adopts the automatic and adaptive step to perfect the BP algorithm. In addition, because the traditional BP neural network is easy to trap into local minimum, this paper makes use of the characteristic of simulated annealing algorithm and let it unite with BP algorithm. Because the simulated annealing algorithm can get optimal approximation by searching local, it can help BP algorithm not to trap into local minimum.
ISBN:9781424452453
1424452457
9780769538990
0769538991
DOI:10.1109/WGEC.2009.39