Stochastic Memristor Modeling Framework Based on Physics-Informed Neural Networks

In this paper, we present a framework of modeling memristor noise for circuit simulators using physics-informed neural networks (PINNs). The variability of the memristor that is directly related to the neuromorphic system can be handled with this approach. The memristor noise model is transformed in...

Full description

Saved in:
Bibliographic Details
Main Authors: Kyeongmin Kim, Jonghwan Lee
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/20/9484
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850204991758794752
author Kyeongmin Kim
Jonghwan Lee
author_facet Kyeongmin Kim
Jonghwan Lee
author_sort Kyeongmin Kim
collection DOAJ
description In this paper, we present a framework of modeling memristor noise for circuit simulators using physics-informed neural networks (PINNs). The variability of the memristor that is directly related to the neuromorphic system can be handled with this approach. The memristor noise model is transformed into a Fokker–Planck equation (FPE) from a probabilistic perspective. The translated equations are physically interpreted through the PINN. The weights and biases extracted from the PINN are implemented in Verilog-A through simple operations. The characteristics of the stochastic system under the noise are obtained by integrating the probability density function. This approach allows for the unification of different memristor models and the analysis of the effects of noise.
format Article
id doaj-art-e221e1f59d7b4a62b1858caf4b2f5312
institution OA Journals
issn 2076-3417
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-e221e1f59d7b4a62b1858caf4b2f53122025-08-20T02:11:11ZengMDPI AGApplied Sciences2076-34172024-10-011420948410.3390/app14209484Stochastic Memristor Modeling Framework Based on Physics-Informed Neural NetworksKyeongmin Kim0Jonghwan Lee1Department of System Semiconductor Engineering, Sangmyung University, Cheonan 31066, Republic of KoreaDepartment of System Semiconductor Engineering, Sangmyung University, Cheonan 31066, Republic of KoreaIn this paper, we present a framework of modeling memristor noise for circuit simulators using physics-informed neural networks (PINNs). The variability of the memristor that is directly related to the neuromorphic system can be handled with this approach. The memristor noise model is transformed into a Fokker–Planck equation (FPE) from a probabilistic perspective. The translated equations are physically interpreted through the PINN. The weights and biases extracted from the PINN are implemented in Verilog-A through simple operations. The characteristics of the stochastic system under the noise are obtained by integrating the probability density function. This approach allows for the unification of different memristor models and the analysis of the effects of noise.https://www.mdpi.com/2076-3417/14/20/9484memristornoisestochasticFokker–Planck equation (FPE)physics-informed neural network (PINN)Verilog-A
spellingShingle Kyeongmin Kim
Jonghwan Lee
Stochastic Memristor Modeling Framework Based on Physics-Informed Neural Networks
Applied Sciences
memristor
noise
stochastic
Fokker–Planck equation (FPE)
physics-informed neural network (PINN)
Verilog-A
title Stochastic Memristor Modeling Framework Based on Physics-Informed Neural Networks
title_full Stochastic Memristor Modeling Framework Based on Physics-Informed Neural Networks
title_fullStr Stochastic Memristor Modeling Framework Based on Physics-Informed Neural Networks
title_full_unstemmed Stochastic Memristor Modeling Framework Based on Physics-Informed Neural Networks
title_short Stochastic Memristor Modeling Framework Based on Physics-Informed Neural Networks
title_sort stochastic memristor modeling framework based on physics informed neural networks
topic memristor
noise
stochastic
Fokker–Planck equation (FPE)
physics-informed neural network (PINN)
Verilog-A
url https://www.mdpi.com/2076-3417/14/20/9484
work_keys_str_mv AT kyeongminkim stochasticmemristormodelingframeworkbasedonphysicsinformedneuralnetworks
AT jonghwanlee stochasticmemristormodelingframeworkbasedonphysicsinformedneuralnetworks