8 citations · 18 across the 8 of their papers we have counts for
8 papers
Exponential discretization of weights of neural network connections in pre-trained neural networks
Magomed Yu. Malsagov, Emil M. Khayrov, Maria M. Pushkareva +1
To reduce random access memory (RAM) requirements and to increase speed of recognition algorithms we consider a weight discretization problem for trained neural networks. We show t…
Investigation of Finite-size 2D Ising Model with a Noisy Matrix of Spin-Spin Interactions
Boris Kryzhanovsky, Magomed Malsagov, Iakov Karandashev
We analyze changes in the thermodynamic properties of a spin system when it passes from the classical two-dimensional Ising model to the spin glass model, where spin-spin interacti…
Dependence of critical parameters of 2D Ising model on lattice size
Boris V. Kryzhanovsky, Magomed Yu. Malsagov, Iakov M. Karandashev
For the 2D Ising model, we analyzed dependences of thermodynamic characteristics on number of spins by means of computer simulations. We compared experimental data obtained using t…
Global Minimum Depth In Edwards-Anderson Model
Iakov Karandashev, Boris Kryzhanovsky
In the literature the most frequently cited data are quite contradictory, and there is no consensus on the global minimum value of 2D Edwards-Anderson (2D EA) Ising model. By means…
The Analytical Expressions for a Finite-Size 2D Ising Model
M. Yu. Malsagov, I. M. Karandashev, B. V. Kryzhanovsky
Numerical methods are used to examine the thermodynamic characteristics of the two-dimensional Ising model as a function of the number of spins N. Onsager's solution is generalized…
An Approximate Backpropagation Learning Rule for Memristor Based Neural Networks Using Synaptic Plasticity
D. V. Negrov, I. M. Karandashev, V. V. Shakirov +3
We describe an approximation to backpropagation algorithm for training deep neural networks, which is designed to work with synapses implemented with memristors. The key idea is to…
Models of Innate Neural Attractors and Their Applications for Neural Information Processing
Ksenia P. Solovyeva, Iakov M. Karandashev, Alex Zhavoronkov +1
In this work we reveal and explore a new class of attractor neural networks, based on inborn connections provided by model molecular markers, the molecular marker based attractor n…
Increasing the attraction area of the global minimum in the binary optimization problem
Iakov Karandashev, Boris Kryzhanovsky
The problem of binary minimization of a quadratic functional in the configuration space is discussed. In order to increase the efficiency of the random-search algorithm it is propo…