DocumentCode :
2234393
Title :
A novel neural network learning method for dynamically tuning regularization coefficient
Author :
Yan, Wu ; Liming, Zhang
Author_Institution :
Dept. of Comput. Sci. & Eng., Tongji Univ., Shanghai, China
Volume :
3
fYear :
2001
fDate :
2001
Firstpage :
516
Abstract :
When network structure has been determined, it is very effective that regulation methods are used to improve generalization ability. However, there are some obvious drawbacks. Based on this, the paper has proposed a novel method that dynamically tune the regularization coefficient by fuzzy rules inference, effectively determined the fuzzy inference rules and membership functions, and implemented the method. Finally, it has compared the method with traditional BP algorithm and fixed regularization coefficient´s method through several examples simulations. The results indicate that the proposed method is a very effective method. Compared with other two methods, the proposed method has the merits of the highest precision, rapid convergence, and the best generalization ability
Keywords :
fuzzy logic; generalisation (artificial intelligence); inference mechanisms; learning (artificial intelligence); neural nets; BP algorithm; backpropagation; dynamic coefficient tuning; fuzzy rules inference; generalization; neural network learning method; regularization coefficient tuning; Computer science; Convergence; Function approximation; Fuzzy neural networks; Inference algorithms; Intelligent control; Learning systems; Neural networks; Optimization methods; Pattern recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Info-tech and Info-net, 2001. Proceedings. ICII 2001 - Beijing. 2001 International Conferences on
Conference_Location :
Beijing
Print_ISBN :
0-7803-7010-4
Type :
conf
DOI :
10.1109/ICII.2001.983109
Filename :
983109
Link To Document :
بازگشت