DocumentCode :
2773150
Title :
Non Iterative Hopfield Model
Author :
Edgar, A.C.S. ; Márquez, Cornelio Yánez
Author_Institution :
Center for Comput. Res., Nat. Polytech. Inst.
Volume :
2
fYear :
2006
fDate :
Sept. 2006
Firstpage :
137
Lastpage :
144
Abstract :
The Hopfield model has problems in the recall phase, one of them it´s the time convergence or non convergence in certain cases. We propose a model that eliminates iteration in Hopfield model. This modification in the recall phase, eliminates the iterations and for consequence takes fewer steps, after them, the recuperation of N patterns learned it´s the same or little better than Hopfield model. Finally because iteration is eliminated the recuperation time is reduced too
Keywords :
Hopfield neural nets; content-addressable storage; convergence; associative memory; noniterative Hopfield model; time convergence; Additive noise; Associative memory; Automotive engineering; Convergence; History; Hopfield neural networks; Neural networks; Neurons; Proposals; Robot kinematics;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Electronics, Robotics and Automotive Mechanics Conference, 2006
Conference_Location :
Cuernavaca
Print_ISBN :
0-7695-2569-5
Type :
conf
DOI :
10.1109/CERMA.2006.67
Filename :
4019784
Link To Document :
بازگشت