loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
First International Conference on Innovative Computing, Information and Control - Volume II (ICICIC'06)
A Novel BP Algorithm Based on Self-adaptive Parameters and Performance Analysis
Beijing, China
August 30-September 01
ISBN: 0-7695-2616-0
ASCII Text
x 
 
Haibin Cai, Liangxu Liu, Qiying Cao, "A Novel BP Algorithm Based on Self-adaptive Parameters and Performance Analysis," Innovative Computing ,Information and Control, International Conference on, vol. 2, pp. 383-387, First International Conference on Innovative Computing, Information and Control - Volume II (ICICIC'06), 2006.
 
 
BibTex
x
 
@article{ 10.1109/ICICIC.2006.213,
author = {Haibin Cai and Liangxu Liu and Qiying Cao},
title = {A Novel BP Algorithm Based on Self-adaptive Parameters and Performance Analysis},
journal ={Innovative Computing ,Information and Control, International Conference on},
volume = {2},
year = {2006},
isbn = {0-7695-2616-0},
pages = {383-387},
doi = {http://doi.ieeecomputersociety.org/10.1109/ICICIC.2006.213},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Innovative Computing ,Information and Control, International Conference on
TI - A Novel BP Algorithm Based on Self-adaptive Parameters and Performance Analysis
SN - 0-7695-2616-0
SP383
EP387
A1 - Haibin Cai,
A1 - Liangxu Liu,
A1 - Qiying Cao,
PY - 2006
KW - null
VL - 2
JA - Innovative Computing ,Information and Control, International Conference on
ER -
 
Haibin Cai, Donghua University, China
Liangxu Liu, Donghua University, China
Qiying Cao, Donghua University, China
The standard back-propagation(BP) algorithm converges slowly and is easy to trap into local minimum, which is the main reason why it cannot be used widely in practical applications. Therefore, a new BP algorithm based on selfadaptive parameters, called the SAPBP algorithm for short, is put forward in this paper. The convergence stability is enhanced by adding the positive matrix in Hessian Matrix. The SAPBP algorithm is used in approximating nonlinear function in order to test its performance. The data of simulation experiment have proved that the improved algorithm can converges very fast and avoid trapping into local minimum. The convergence stability, also, is very good. The results demonstrate the proposed scheme is efficient, and has good performance.
Citation:
Haibin Cai, Liangxu Liu, Qiying Cao, "A Novel BP Algorithm Based on Self-adaptive Parameters and Performance Analysis," icicic, vol. 2, pp.383-387, First International Conference on Innovative Computing, Information and Control - Volume II (ICICIC'06), 2006
Usage of this product signifies your acceptance of the Terms of Use.