Associative memories with "killed" neurons: The methods of recovery

We consider re-learning ability of a Hopfield-type network after killing some neurons. Neurons were "killed" by means of nullification of corresponding rows and columns of the synaptic matrix. We show that one can restore recognition ability of this network using re-training with the vecto...

Full description

Saved in:
Bibliographic Details
Published inProceedings of the International Joint Conference on Neural Networks, 2003 Vol. 4; pp. 2579 - 2582 vol.4
Main Authors Reznik, A.M., Sitchov, A.S., Dekhtyarenko, O.K., Nowicki, D.W.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2003
Subjects
Adaptive filters
Associative memory
Convergence
Equations
Hopfield neural networks
Neural networks
Neurons
Stability
Vectors
Online AccessGet full text

Cover

More Information
Summary:We consider re-learning ability of a Hopfield-type network after killing some neurons. Neurons were "killed" by means of nullification of corresponding rows and columns of the synaptic matrix. We show that one can restore recognition ability of this network using re-training with the vectors, which were memorized before. The number of vectors needed is equal to the number of deleted neurons. It does not depend on network's size and on volume of stored data.
ISBN:9780780378988
0780378989
ISSN:1098-7576
1558-3902
DOI:10.1109/IJCNN.2003.1223972