activity
19992004
collaborators

6 papers

cond-mat.dis-nn2004

Vector-Neuron Models of Associative Memory

B. V. Kryzhanovsky, L. B. Litinskii, A. L. Mikaelian

We consider two models of Hopfield-like associative memory with -valued neurons: Potts-glass neural network (PGNN) and parametrical neural network (PNN). In these models neurons…

cond-mat.dis-nn2001

Some rigorous results for the Hopfield Model

L. B. Litinskii

For the Hopfield model with the Hebb connection matrix we investigate the case of memorized patterns that are distorted copies of the same {\it standard}. In other words, we tr…

cond-mat.dis-nn2000

On the problem of neural network decomposition into some subnets

Leonid B. Litinskii

An artificial neural network is usually treated as a whole system, being characterized by its ground state (the global minimum of the energy functional), the set of fixed points, t…

cond-mat.dis-nn1999

Generalization in the Hopfield Model

Leonid B. Litinskii

In the Hopfield model the ability of the network to generalization is studied in the case of the network trained by one input image ({\it the standard}).

cond-mat.dis-nn1999

Energy Functional and Fixed Points of a Neural Networks

Leonid B. Litinskii

It turned out that the set of the fixed points is not necessarily the same as the set of the local minima of the energy functional. It depends on the diagonal elements of the conne…

cond-mat.dis-nn1999

Fixed points of Hopfield type neural networks

Leonid B. Litinskii

The set of the fixed points of the Hopfield type network is under investigation. The connection matrix of the network is constructed according the Hebb rule from the set of memoriz…