Mikhail Kryzhanovsky

Learn More
Probability of neuronal spike initiation was considered within the framework of a simple stochastic model. The time of spike occurrence was defined as the first time crossing of a stochastic process and a determined time function. This problem has been investigated in the case of a stationary Gaussian stochastic process and a linear time function. An(More)
This article offers two methods of scheduling, based on artificial neural networks. The first one is based on vector networks and the second method is based on Hopfield scalar model. The article contains a detailed description of each algorithm. At the end of the article, the results of computer experiments are presented, where a comparison of algorithms(More)
The paper treats the issue of pattern recognition training in terms of Hopfield associative memory (HAM). The conventional randomization technique is used to determine the exponential extremity of HAM recognition error. The extremity exponent is considered as a function of the training process. In training, the exponent is shown to rise from (1-2p) 4 to(More)
Applicability of clipping of quadratic functional E = −0.5x + Tx + Bx in the minimization problem is considered (here x is the configurational vector and B ∈ R N is real valued vector). The probability that the gradient of this functional and the gradient of clipped functional ɛ = −0.5x + τx + bx are collinear is shown to be very high (the matrix τ is(More)
The capability of discretization of matrix elements in the problem of quadratic functional minimization with linear member built on matrix in N-dimensional configuration space with discrete coordinates is researched. It is shown, that optimal procedure of replacement matrix elements by the integer quantities with the limited number of gradations exist, and(More)
The paper treats the issue of pattern recognition training in terms of Hopfield associative memory (HAM). The conventional randomization technique is used to determine the exponential extremity of HAM recognition error. The extremity exponent is considered as a function of the training process. In training, the exponent is shown to rise from (1-2p) 4 to(More)
  • 1