Machine learning-powered compact modeling of stochastic electronic devices using mixture density networks
Abstract The relentless pursuit of miniaturization and performance enhancement in electronic devices has led to a fundamental challenge in the field of circuit design and simulation-how to accurately account for the inherent stochastic nature of certain devices. While conventional deterministic mode...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2024-03-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-024-56779-8 |
_version_ | 1797259354631569408 |
---|---|
author | Jack Hutchins Shamiul Alam Dana S. Rampini Bakhrom G. Oripov Adam N. McCaughan Ahmedullah Aziz |
author_facet | Jack Hutchins Shamiul Alam Dana S. Rampini Bakhrom G. Oripov Adam N. McCaughan Ahmedullah Aziz |
author_sort | Jack Hutchins |
collection | DOAJ |
description | Abstract The relentless pursuit of miniaturization and performance enhancement in electronic devices has led to a fundamental challenge in the field of circuit design and simulation-how to accurately account for the inherent stochastic nature of certain devices. While conventional deterministic models have served as indispensable tools for circuit designers, they fall short when it comes to capturing the subtle yet critical variability exhibited by many electronic components. In this paper, we present an innovative approach that transcends the limitations of traditional modeling techniques by harnessing the power of machine learning, specifically Mixture Density Networks (MDNs), to faithfully represent and simulate the stochastic behavior of electronic devices. We demonstrate our approach to model heater cryotrons, where the model is able to capture the stochastic switching dynamics observed in the experiment. Our model shows 0.82% mean absolute error for switching probability. This paper marks a significant step forward in the quest for accurate and versatile compact models, poised to drive innovation in the realm of electronic circuits. |
first_indexed | 2024-04-24T23:08:06Z |
format | Article |
id | doaj.art-633041add4dc409fa1532145bbae389a |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-04-24T23:08:06Z |
publishDate | 2024-03-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-633041add4dc409fa1532145bbae389a2024-03-17T12:21:44ZengNature PortfolioScientific Reports2045-23222024-03-011411910.1038/s41598-024-56779-8Machine learning-powered compact modeling of stochastic electronic devices using mixture density networksJack Hutchins0Shamiul Alam1Dana S. Rampini2Bakhrom G. Oripov3Adam N. McCaughan4Ahmedullah Aziz5Department of Electrical Engineering & Computer Science, University of TennesseeDepartment of Electrical Engineering & Computer Science, University of TennesseeNational Institute of Standards and TechnologyNational Institute of Standards and TechnologyNational Institute of Standards and TechnologyDepartment of Electrical Engineering & Computer Science, University of TennesseeAbstract The relentless pursuit of miniaturization and performance enhancement in electronic devices has led to a fundamental challenge in the field of circuit design and simulation-how to accurately account for the inherent stochastic nature of certain devices. While conventional deterministic models have served as indispensable tools for circuit designers, they fall short when it comes to capturing the subtle yet critical variability exhibited by many electronic components. In this paper, we present an innovative approach that transcends the limitations of traditional modeling techniques by harnessing the power of machine learning, specifically Mixture Density Networks (MDNs), to faithfully represent and simulate the stochastic behavior of electronic devices. We demonstrate our approach to model heater cryotrons, where the model is able to capture the stochastic switching dynamics observed in the experiment. Our model shows 0.82% mean absolute error for switching probability. This paper marks a significant step forward in the quest for accurate and versatile compact models, poised to drive innovation in the realm of electronic circuits.https://doi.org/10.1038/s41598-024-56779-8 |
spellingShingle | Jack Hutchins Shamiul Alam Dana S. Rampini Bakhrom G. Oripov Adam N. McCaughan Ahmedullah Aziz Machine learning-powered compact modeling of stochastic electronic devices using mixture density networks Scientific Reports |
title | Machine learning-powered compact modeling of stochastic electronic devices using mixture density networks |
title_full | Machine learning-powered compact modeling of stochastic electronic devices using mixture density networks |
title_fullStr | Machine learning-powered compact modeling of stochastic electronic devices using mixture density networks |
title_full_unstemmed | Machine learning-powered compact modeling of stochastic electronic devices using mixture density networks |
title_short | Machine learning-powered compact modeling of stochastic electronic devices using mixture density networks |
title_sort | machine learning powered compact modeling of stochastic electronic devices using mixture density networks |
url | https://doi.org/10.1038/s41598-024-56779-8 |
work_keys_str_mv | AT jackhutchins machinelearningpoweredcompactmodelingofstochasticelectronicdevicesusingmixturedensitynetworks AT shamiulalam machinelearningpoweredcompactmodelingofstochasticelectronicdevicesusingmixturedensitynetworks AT danasrampini machinelearningpoweredcompactmodelingofstochasticelectronicdevicesusingmixturedensitynetworks AT bakhromgoripov machinelearningpoweredcompactmodelingofstochasticelectronicdevicesusingmixturedensitynetworks AT adamnmccaughan machinelearningpoweredcompactmodelingofstochasticelectronicdevicesusingmixturedensitynetworks AT ahmedullahaziz machinelearningpoweredcompactmodelingofstochasticelectronicdevicesusingmixturedensitynetworks |