Mathematical Modeling of an Analogue Self-Learning Neural Network Based on Memristive Elements Taking into Account Stochastic Switching Dynamics

Morozov, A. Yu.; Abgaryan, K. K.; Ревизников, Д. Л.

doi:10.1134/s263516762106015x

Cited by 4 publications

(9 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A detailed description of the model is given in refs. [19][20][21]35]. In this article, the model has been modified to take into account the interval nature of the variables.…”

Section: Simulation Modeling Of the Neuromorphic Networkmentioning

confidence: 99%

“…We can observe that the adaptation of the weights to the recognizable patterns occurs at different rates and the patterns are distributed among the neurons randomly, which corresponds to the results of ref. [19].…”

Section: Simulation Modeling Of the Neuromorphic Networkmentioning

confidence: 99%

“…At the same time, in contrast to ref. [19], in interval approach, there is no need to solve stochastic ODEs, which simplifies the modeling process and reduces computational costs. Since interval estimates fully contain the experimental data, it is possible to study how the current-voltage dispersion affects the quality of neuromorphic computing.…”

Section: Simulation Modeling Of the Neuromorphic Networkmentioning

confidence: 99%

“…[16][17][18] Previously, the authors considered an approach to replacing the deterministic equation of state with a stochastic one by introducing a term responsible for additive (Gaussian) noise. [19][20][21][22] In this article, we propose to use the interval apparatus to take into account the scatter in the characteristics of elements. The idea is to introduce interval parameters into the mathematical model.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Interval Model of a Memristor Crossbar Network

Morozov

Abgaryan

Ревизников

2022

Physica Status Solidi (b)

View full text Add to dashboard Cite

This article covers the modeling of memristive oxide‐based elements within the context of a complex simulation model of an analog self‐learning spiking neural network. According to the experimental data, the nature of the memristor operation is stochastic, as evidenced by the variation in the current–voltage characteristics for different resistive switching cycles. Often, the existing mathematical models of memristors do not fully reproduce the experimental results, which can adversely affect the accuracy of neuromorphic network simulation. It is proposed to use the interval approach to take into account the variations in the element characteristics. The idea is to introduce interval parameters into the mathematical model. Thus, the simulation results at each moment are interval estimates of phase variables. The values of interval parameters are calculated in such a way that the intervals completely contain the experimental data. When simulating the operation of the entire analog self‐learning spiking neural network, at each training epoch the parameters of the memristors are set randomly from the found intervals. The approbation of the proposed approach is carried out on the problem of pattern recognition by the crossbar architecture network with the LiNbO3‐based memristive elements.

show abstract

“…A detailed description of the model is given in refs. [19][20][21]35]. In this article, the model has been modified to take into account the interval nature of the variables.…”

Section: Simulation Modeling Of the Neuromorphic Networkmentioning

confidence: 99%

Section: Simulation Modeling Of the Neuromorphic Networkmentioning

confidence: 99%

Section: Simulation Modeling Of the Neuromorphic Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Interval Model of a Memristor Crossbar Network

Morozov

Abgaryan

Ревизников

2022

Physica Status Solidi (b)

View full text Add to dashboard Cite

show abstract

“…Such models, being computationally quite economical, can be effectively used in simulation modeling of neuromorphic systems based on memristor crossbars. [ 23,24 ]…”

Section: Introductionmentioning

confidence: 99%

Multiscale Modeling of Ion Dynamics in Memristive Elements

Zhuravlev

Abgaryan

Ревизников

2022

Physica Status Solidi (b)

View full text Add to dashboard Cite

A multiscale computational scheme is proposed for ion dynamics that allows modeling based on primary information—data on the chemical composition of the material and its crystal structure. The scheme includes quantum mechanical and molecular dynamics modeling as well as Monte Carlo simulation of ion and electron dynamics taking into account the real crystal structure. Approbation of the proposed approach is carried out on a silicon oxide memristive element. The results of computational experiments are presented that demonstrate the stages of growth and destruction of a conductive filament under the action of a time‐varying voltage.

show abstract

Design and Implementation of English Teaching Analysis System Based on BP Neural Network Algorithm

Zhang

Chen

2023

Lecture Notes on Data Engineering and Communications Technologies

View full text Add to dashboard Cite

Mathematical Modeling of an Analogue Self-Learning Neural Network Based on Memristive Elements Taking into Account Stochastic Switching Dynamics

Cited by 4 publications

References 37 publications

Interval Model of a Memristor Crossbar Network

Interval Model of a Memristor Crossbar Network

Multiscale Modeling of Ion Dynamics in Memristive Elements

Design and Implementation of English Teaching Analysis System Based on BP Neural Network Algorithm

Contact Info

Product

Resources

About