AI-guided framework for the design of materials and devices for magnetic-tunnel-junction-based true random number generators

Abstract Emerging devices, such as magnetic tunnel junctions, are key for energy-efficient, performant future computing systems. However, designing devices with the desirable specification and performance for these applications is often found to be time-consuming and non-trivial. Here, we investigat...

Full description

Saved in:
Bibliographic Details
Main Authors: Karan P. Patel, Andrew Maicke, Jared Arzate, Jaesuk Kwon, J. Darby Smith, James B. Aimone, Jean Anne C. Incorvia, Suma G. Cardwell, Catherine D. Schuman
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Communications Engineering
Online Access:https://doi.org/10.1038/s44172-025-00376-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849774362906853376
author Karan P. Patel
Andrew Maicke
Jared Arzate
Jaesuk Kwon
J. Darby Smith
James B. Aimone
Jean Anne C. Incorvia
Suma G. Cardwell
Catherine D. Schuman
author_facet Karan P. Patel
Andrew Maicke
Jared Arzate
Jaesuk Kwon
J. Darby Smith
James B. Aimone
Jean Anne C. Incorvia
Suma G. Cardwell
Catherine D. Schuman
author_sort Karan P. Patel
collection DOAJ
description Abstract Emerging devices, such as magnetic tunnel junctions, are key for energy-efficient, performant future computing systems. However, designing devices with the desirable specification and performance for these applications is often found to be time-consuming and non-trivial. Here, we investigate the design and optimization of spin–orbit torque and spin transfer torque magnetic tunnel junction models as the probabilistic devices for true random number generation. We leverage reinforcement learning and evolutionary optimization to vary key device and material properties of the various device models for stochastic operation. Our artificial-intelligence-guided codesign methods generated different candidate devices capable of generating stochastic samples for a desired probability distribution, while also minimizing energy usage for the devices. This framework can also be applied to other devices and applications.
format Article
id doaj-art-c5b25db16aaf46f89fe7472cddc0b696
institution DOAJ
issn 2731-3395
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Communications Engineering
spelling doaj-art-c5b25db16aaf46f89fe7472cddc0b6962025-08-20T03:01:43ZengNature PortfolioCommunications Engineering2731-33952025-03-014111110.1038/s44172-025-00376-8AI-guided framework for the design of materials and devices for magnetic-tunnel-junction-based true random number generatorsKaran P. Patel0Andrew Maicke1Jared Arzate2Jaesuk Kwon3J. Darby Smith4James B. Aimone5Jean Anne C. Incorvia6Suma G. Cardwell7Catherine D. Schuman8Department of Electrical Engineering and Computer Science, University of TennesseeChandra Family Dept. of Electrical and Computer Engineering, The University of Texas at AustinChandra Family Dept. of Electrical and Computer Engineering, The University of Texas at AustinChandra Family Dept. of Electrical and Computer Engineering, The University of Texas at AustinSandia National LaboratoriesSandia National LaboratoriesChandra Family Dept. of Electrical and Computer Engineering, The University of Texas at AustinSandia National LaboratoriesDepartment of Electrical Engineering and Computer Science, University of TennesseeAbstract Emerging devices, such as magnetic tunnel junctions, are key for energy-efficient, performant future computing systems. However, designing devices with the desirable specification and performance for these applications is often found to be time-consuming and non-trivial. Here, we investigate the design and optimization of spin–orbit torque and spin transfer torque magnetic tunnel junction models as the probabilistic devices for true random number generation. We leverage reinforcement learning and evolutionary optimization to vary key device and material properties of the various device models for stochastic operation. Our artificial-intelligence-guided codesign methods generated different candidate devices capable of generating stochastic samples for a desired probability distribution, while also minimizing energy usage for the devices. This framework can also be applied to other devices and applications.https://doi.org/10.1038/s44172-025-00376-8
spellingShingle Karan P. Patel
Andrew Maicke
Jared Arzate
Jaesuk Kwon
J. Darby Smith
James B. Aimone
Jean Anne C. Incorvia
Suma G. Cardwell
Catherine D. Schuman
AI-guided framework for the design of materials and devices for magnetic-tunnel-junction-based true random number generators
Communications Engineering
title AI-guided framework for the design of materials and devices for magnetic-tunnel-junction-based true random number generators
title_full AI-guided framework for the design of materials and devices for magnetic-tunnel-junction-based true random number generators
title_fullStr AI-guided framework for the design of materials and devices for magnetic-tunnel-junction-based true random number generators
title_full_unstemmed AI-guided framework for the design of materials and devices for magnetic-tunnel-junction-based true random number generators
title_short AI-guided framework for the design of materials and devices for magnetic-tunnel-junction-based true random number generators
title_sort ai guided framework for the design of materials and devices for magnetic tunnel junction based true random number generators
url https://doi.org/10.1038/s44172-025-00376-8
work_keys_str_mv AT karanppatel aiguidedframeworkforthedesignofmaterialsanddevicesformagnetictunneljunctionbasedtruerandomnumbergenerators
AT andrewmaicke aiguidedframeworkforthedesignofmaterialsanddevicesformagnetictunneljunctionbasedtruerandomnumbergenerators
AT jaredarzate aiguidedframeworkforthedesignofmaterialsanddevicesformagnetictunneljunctionbasedtruerandomnumbergenerators
AT jaesukkwon aiguidedframeworkforthedesignofmaterialsanddevicesformagnetictunneljunctionbasedtruerandomnumbergenerators
AT jdarbysmith aiguidedframeworkforthedesignofmaterialsanddevicesformagnetictunneljunctionbasedtruerandomnumbergenerators
AT jamesbaimone aiguidedframeworkforthedesignofmaterialsanddevicesformagnetictunneljunctionbasedtruerandomnumbergenerators
AT jeanannecincorvia aiguidedframeworkforthedesignofmaterialsanddevicesformagnetictunneljunctionbasedtruerandomnumbergenerators
AT sumagcardwell aiguidedframeworkforthedesignofmaterialsanddevicesformagnetictunneljunctionbasedtruerandomnumbergenerators
AT catherinedschuman aiguidedframeworkforthedesignofmaterialsanddevicesformagnetictunneljunctionbasedtruerandomnumbergenerators