Statistical Physical Properties of Four-Wave Mixing Optical Neural Network
PDF (Russian)


optical neural network
Ising model
long-range interaction
n-coherence method

How to Cite

Kryzhanovsky B.V., Litinsky L.B. Statistical Physical Properties of Four-Wave Mixing Optical Neural Network // Russian Journal of Cybernetics. 2021. Vol. 2, № 4. P. 42-48. DOI: 10.51790/2712-9942-2021-2-4-4.


The paper investigates the statistical physical properties of an optical neural network. The conditions for training a neural network by the maximum likelihood algorithm are identified. The study uses a three-dimensional Ising model, to which a long-range action is sequentially added so that in the limit the model can be described by the mean-field theory. Analytical estimates of the critical neural network temperature were obtained considering the interaction with the second and third-order neighbors. The estimates for the entire interval of the interaction parameters are in good agreement with the results obtained by Monte Carlo methods. It is found that as the number of positive interconnections increase, the critical temperature value decreases and the maximum likelihood algorithm can be applied virtually without any restrictions.
PDF (Russian)


Carreira-Perpiñán M. Á., Hinton G. On Contrastive Divergence Learning. Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics, PMLR R5:33-40, 2005.

Hinton G. E. Training Products of Experts by Minimizing Contrastive Divergence. Neural Computation. 2002;14(9):1771-1800.

Доценко В. С. Физика спин-стекольного состояния. УФН. 1993;163:1.

Patashinskii A. Z., Pokrovskii V. L. Fluctuation Theory of Phase Transitions. Oxford: Pergamon Pr.; 1979.

Butera P., Comi M. Critical Universality and Hyperscaling Revisited for Ising Models of General Spin Using Extended High-Temperature Series. Phys. Rev. B. 2002;65:144431.

Morozov O. G., Sakhabutdinov A. J. Addressed Fiber Bragg Structures in Quasi-Distributed Microwave-Photonic Sensor Systems. Computer Optics. 2019;43:535-543.

Муртазаев А. К., Рамазанов М. К., Касан-Оглы Ф. А., Курбанова Д. Р. Фазовый переход в антиферромагнитной модели Изинга. ЖЭТФ. 2015;147:127.

Häggkvist R. et al. On the Ising Model for the Simple Cubic Lattice. Advances in Physics. 2007;56:653-755.

Крыжановский Б. В., Литинский Л. Б. Обобщенное уравнение Брегга-Вильямса для систем с произвольным дальнодействием. ДАН. 2014;459(6):680-684.

Kryzhanovsky B., Litinskii L. Applicability of n-vicinity Method for Calculation of Free Energy of Ising Model. Physica A. 2017;468:493–507.

Kryzhanovsky B. V., Kryzhanovsky V. M., Mikaelian A. L., Fonarev A. Parametric Dynamic Neural Network Recognition Power. Optical Memory & Neural Network. 2001;10(4):211-218.

Крыжановский Б. В., Микаэлян А. Л. О распознающей способности нейросети на нейронах с параметрическим преобразованием частот. ДАН. 2002;383:318-321.


Download data is not yet available.