DocumentCode :
397633
Title :
Multi-branch neural networks with Branch Control
Author :
Yamashita, Takashi ; Hirasawa, Kotaro ; Hu, Jinglu
Author_Institution :
Kyushu Univ., Fukuoka, Japan
Volume :
1
fYear :
2003
fDate :
5-8 Oct. 2003
Firstpage :
756
Abstract :
Multi-branch neural networks have been proposed already in order to realize compact networks. It uses some branches between nodes, and this can improve the learning and generalization ability of the networks. In this paper, Branch Control is proposed on the multi-branch neural networks to further enhance the learning and generalization ability of the networks. Branch Control is to adjust the values of the signals on the branches depending on the network inputs using an additional branch control network. It has been clarified from simulation results of a function approximation problem that multi-branch neural networks with Branch Control could be improved more than that without Branch Control.
Keywords :
function approximation; generalisation (artificial intelligence); learning (artificial intelligence); neural nets; branch control network; function approximation; generalization ability; learning ability; multibranch neural networks; Biological neural networks; Cellular neural networks; Cities and towns; Delay effects; Function approximation; Neural networks;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Systems, Man and Cybernetics, 2003. IEEE International Conference on
ISSN :
1062-922X
Print_ISBN :
0-7803-7952-7
Type :
conf
DOI :
10.1109/ICSMC.2003.1243905
Filename :
1243905
Link To Document :
بازگشت