DocumentCode :
1386216
Title :
On the synthesis of nonlinear continuous neural networks
Author :
Das, Samir Ranjan
Author_Institution :
Indian Stat. Inst., Calcutta, India
Volume :
21
Issue :
2
fYear :
1991
Firstpage :
413
Lastpage :
418
Abstract :
A synthesis technique for a class of nonlinear neural networks that subsumes J.J. Hopfield´s network with graded response (1984) is presented. The network is synthesized by designing its energy function E such that the function has local minima at the prescribed attractor points. Implementation of the synthesis technique as a nonlinear programming problem is also suggested
Keywords :
neural nets; attractor points; energy function; graded response network; local minima; neural network synthesis; nonlinear continuous neural networks; nonlinear programming; Differential equations; Hopfield neural networks; Network synthesis; Neural networks; Neurons;
fLanguage :
English
Journal_Title :
Systems, Man and Cybernetics, IEEE Transactions on
Publisher :
ieee
ISSN :
0018-9472
Type :
jour
DOI :
10.1109/21.87077
Filename :
87077
Link To Document :
بازگشت