DocumentCode :
1749037
Title :
Generalization in the Hopfield model
Author :
Litinskii, Leonid B.
Author_Institution :
High Pressure Phys. Inst., Acad. of Sci., Troitsk, Russia
Volume :
1
fYear :
2001
fDate :
2001
Firstpage :
65
Abstract :
For the Hopfield model with the Hebb connection matrix we investigate the case of p memorized patterns that are distorted copies of the same n-dimensional standard. In other words, we try to simulate that learning always takes place by means of repeating presentations of one and the same standard, and the presentations are accompanied by distortions of the standard. We obtain some rigorous results relating to dependence of the learning quality on external parameters of the problem
Keywords :
Hebbian learning; Hopfield neural nets; generalisation (artificial intelligence); matrix algebra; Hebb connection matrix; Hopfield model; distorted copies; generalization; learning quality; memorized patterns; Electronic mail; Hopfield neural networks; Neural networks; Physics;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location :
Washington, DC
ISSN :
1098-7576
Print_ISBN :
0-7803-7044-9
Type :
conf
DOI :
10.1109/IJCNN.2001.938993
Filename :
938993
Link To Document :
بازگشت