DocumentCode
2103281
Title
Integration of TACO and BP Neural Network
Author
Jing Leng
Author_Institution
Dept. of Inf. Technol., Hubei Univ. of Police, Wuhan
fYear
2008
fDate
21-22 Dec. 2008
Firstpage
103
Lastpage
106
Abstract
As one of the extensive applications of artificial neural network, BP algorithm has some shortcomings such as local optimum. In this paper, we propose a new method--TACO-BP algorithm to train neural network, which may overcome the shortcoming. Firstly, we give description about the TACO-BP. After experiments, we compare the performance between TACO-BPNN and BPNN. Lastly, we analyze the results of the experiments.
Keywords
backpropagation; learning (artificial intelligence); optimisation; artificial neural network; backpropagation neural network; time based ant colony optimization; Acceleration; Artificial intelligence; Artificial neural networks; Convergence; Genetic algorithms; Information technology; Intelligent networks; Multi-layer neural network; Neural networks; Optimization methods; Artificial Neural Networks; BP; TACO;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Information Technology Application Workshops, 2008. IITAW '08. International Symposium on
Conference_Location
Shanghai
Print_ISBN
978-0-7695-3505-0
Type
conf
DOI
10.1109/IITA.Workshops.2008.75
Filename
4731891
Link To Document