[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122790-en":3,"doc-seo-122790-105":29,"detail-sidebar-cat-0-en-105":89},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":11},122790,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Machine Learning Quantum Systems with Magnetic p-bits","Slowing down Moore’s Law intensifies the need for scalable, energy-efficient hardware tailored to modern AI workloads. Probabilistic computing using p-bits has emerged as a domain-specific approach well suited to probabilistic algorithms and applications. Spintronic devices such as stochastic magnetic tunnel junctions (sMTJ) offer a promising route to integrated p-computers. This work studies how such magnetic p-bits can support an emerging intersection between machine learning and quantum physics, targeting quantum many-body problems through probabilistic sampling and learning.","arXiv :2310 .06679v1 [ cs .ET] 10 Oct 2023  \nMachine Learning Quantum Systems with Magnetic p-bits  \nShuvro Chowdhury 1,◦ , Member, IEEE, Kerem Y. Camsari 1,† Senior Member, IEEE  \n1Department of Electrical and Computer Engineering, University of California, Santa Barbara,  \nSanta Barbara, CA, 93106, USA  \n◦ [schowdhury@ece.ucsb.edu](schowdhury@ece.ucsb.edu),†[camsari@ece.ucsb.edu](camsari@ece.ucsb.edu)  \nThe slowing down of Moore’s Law has led to a crisis as the computing workloads of Artificial Intelligence (AI) algorithms continue skyrocketing. There is an urgent need for scalable and energy-efficient hardware catering to the unique requirements of AI algorithms and applications. In this environment, probabilistic computing with p-bits emerged as a scalable, domain-specific, and energy-efficient computing paradigm, particularly useful for probabilistic applications and algorithms.  \nIn particular, spintronic devices such as stochastic magnetic tunnel junctions (sMTJ) show great promise in designing integrated p-computers. Here, we examine how a scalable probabilistic computer with such magnetic p-bits can be useful for an emerging field combining machine learning and quantum physics.  \nIndex Terms—probabilistic bits, probabilistic computation, stochastic magnetic tunnel junctions, spintronics, probabilistic machine learning, quantum many-body problem  \nI. INTRODUCTION  \nWITH the slowing down of Moore’s Law, initial efforts  \nto “re-invent the transistor” met significant challenges [1] . An emerging idea in the field has been to augment the capabilities of the CMOS transistor, instead of finding a drop-in replacement in integrated CMOS + X architectures. Here, we describe how CMOS + spintronics technology, in particular, stochastic magnetic tunnel junctions can be an energy-efficient building block to solve the quantum manybody problems with probabilistic computers.  \nThe idea of a probabilistic computer with probabilistic building blocks can be tied back to a famous talk given by Feynman [2] widely credited for starting the field of quantum computation. In this talk, Feynman also described a probabilistic computer with the same basic idea that mapping a problem to the evolution of a physical system allows energy-efficient, natural computation. In the last few years, the concept of building such a probabilistic computer with p-bits [3] has attracted significant attention with a wide range of applications from combinatorial optimization [4] to machine learning [5] .  \nII. SPINTRONICS FOR PROBABILISTIC COMPUTATION  \nThere are many possible physical implementations of probabilistic bits: digital approximations using pseudo-random number generators [4], single photon avalanche diodes [6], diffusive memristors [7] and other naturally noisy devices. We believe, however, that spintronic technology in the form of CMOS-integrated magnetic tunnel junctions holds the greatest promise in designing scalable p-computers to transform machine learning and AI applications.  \nDesigning magnetic tunnel junctions out of low-energy barrier nanomagnets (LBM) allows a steady stream of noisy bits in highly compact circuit topologies. In recent years, the potential of fast fluctuations (down to nanoseconds) using sMTJs with in-plane magnetic anisotropy has been experimentally demonstrated [8], [9] following theoretical expectations  \nHybrid Probabilistic-Classical Computer  \nProbabilistic Computer  \nFig. 1. (Top) Stochastic magnetic tunnel junction-based p-bit. The bottom layer of the MTJ has been modified to a low-barrier (∼ 0 kT) magnet to achieve the stochastic behavior. (Bottom) A hybrid probabilistic-classical computer where the p-computer solves the computationally hard problem of obtaining probabilistic samples from a given set of weights and the classical computer finds the new weights based on the provided samples.  \n[10] . The sheer scalability of CMOS-integrated MTJ technology, along with extremely compact p-bits operating at room tempera","cbCair0J4mv6bkw1","https://ap.wps.com/l/cbCair0J4mv6bkw1","pdf",2676010,1,3,"English","en",105,"# Introduction\n# Spintronics for Probabilistic Computation\n# Machine Learning Quantum Systems with P-bits","[{\"question\":\"Why does the document argue that scalable, energy-efficient hardware is urgently needed for AI?\",\"answer\":\"It states that the slowing down of Moore’s Law has created a crisis because AI workloads keep increasing, requiring new hardware that can scale efficiently for AI applications.\"},{\"question\":\"What hardware approach does the document highlight for implementing p-bits?\",\"answer\":\"It emphasizes spintronic technology, especially CMOS-integrated magnetic tunnel junctions, as a promising physical implementation for scalable p-computers.\"},{\"question\":\"How does the document connect machine learning to quantum many-body problems using p-bits?\",\"answer\":\"It describes using stochastic neural networks (e.g., restricted Boltzmann Machines) as a variational approach to approximate quantum solutions, and then mapping the model onto hardware-amenable sparse p-bit networks to perform learning and reinforcement in parallel with a classical computer.\"}]","Machine Learning Quantum Systems with Magnetic p-bits | PDF",1785812904,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":28},"machine-learning-quantum-systems-with-magnetic-p-bits","",{"@graph":35,"@context":83},[36,52,66],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,49],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":21},"https://docshare.wps.com/document/research-report/",{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/machine-learning-quantum-systems-with-magnetic-p-bits/122790/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":23,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"Why does the document argue that scalable, energy-efficient hardware is urgently needed for AI?","Question",{"text":73,"@type":74},"It states that the slowing down of Moore’s Law has created a crisis because AI workloads keep increasing, requiring new hardware that can scale efficiently for AI applications.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"What hardware approach does the document highlight for implementing p-bits?",{"text":78,"@type":74},"It emphasizes spintronic technology, especially CMOS-integrated magnetic tunnel junctions, as a promising physical implementation for scalable p-computers.",{"name":80,"@type":71,"acceptedAnswer":81},"How does the document connect machine learning to quantum many-body problems using p-bits?",{"text":82,"@type":74},"It describes using stochastic neural networks (e.g., restricted Boltzmann Machines) as a variational approach to approximate quantum solutions, and then mapping the model onto hardware-amenable sparse p-bit networks to perform learning and reinforcement in parallel with a classical computer.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":45,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":104,"slug":136},19,"General","general"]