DocumentCode :
295749
Title :
Local-sparse connection multilayer networks
Author :
Yongke, Zhang ; Yongjun, Zhang ; Wei, Ye
Author_Institution :
Southwest Inst. of Tech. Phys., Sichuan, China
Volume :
3
fYear :
1995
fDate :
Nov/Dec 1995
Firstpage :
1254
Abstract :
This paper describes a method for reducing the connection weight number in neural networks. Hopfield networks and perception networks are usually fully connected networks. The weight number increases dramatically with neuron number. We construct a kind of local-sparse connection network and give a simulated result to decide the hidden node number
Keywords :
feedforward neural nets; learning (artificial intelligence); network topology; neural net architecture; Hopfield networks; connection weight numbers; hidden node; local-sparse connection networks; multilayer neural networks; neurons; perception networks; Nonhomogeneous media; Robot control;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
Type :
conf
DOI :
10.1109/ICNN.1995.487335
Filename :
487335
Link To Document :
بازگشت