[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128712-en":3,"doc-seo-128712-105":31,"detail-sidebar-cat-0-en-105":92},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128712,962084926284,"Aurora","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Machine Learning-Enhanced Numerical Modeling of Modern Magnetoresistive Memories - Dissertation","Machine learning–assisted computational optimization targets modern magnetoresistive memories to address standby power growth caused by further semiconductor device down-scaling and leakage currents. Magnetoresistive RAM is presented as a non-volatile CMOS-compatible alternative offering high speed and endurance. The work centers on time-dependent magnetization dynamics governed by the Landau-Lifshitz-Gilbert equation, enhanced with torque-related terms needed for MRAM operation. First, FEM-based computation of the demagnetizing field and open-boundary remedies are analyzed and benchmarked. Second, reinforcement learning is combined with micromagnetic simulations to autonomously discover switching pulse sequences, enabling transfer across varying material parameters and optimization goals including fast reversal and energy-efficient switching, extended to SOT-assisted STT-MRAM.","D I S S E R T A T I O N  \nMachine Learning-Enhanced Numerical Modeling of Modern Magnetoresistive Memories  \nausgeführt zum Zwecke der Erlangung des akademischen Grades eines Doktors der technischen Wissenschaften  \nunter der Betreuung von  \nPrivatdoz. MSc PhD Viktor Sverdlov  \neingereicht an der Technischen Universität Wien Fakultät für Elektrotechnik und Informationstechnik  \nvon  \nJohannes Ender, MSc .  \nMatrikelnummer: 01629746  \nWien, im März 2024    \nAbstract  \nThe continuous down-scaling of semiconductor devices over the past decades has led to higher integration density but also higher standby power consumption due to increased leakage currents. Novolatile memory is a promising solution to this problem. Magnetoresistive random access memory (MRAM) poses to be a suitable non-volatile alternative due to its straightforward architecture and compatibility with CMOS technology. It oﬀers the beneﬁts of high speed and excellent endurance, making it an attractive choice for a variety of applications including IoT and automotive applications, as well as embedded DRAM and last-level cache memory. Eﬀective simulation tools provide crucial insights for designing MRAM devices. The process of understanding how the magnetization changes over time in these devices, involves solving the Landau-Lifshitz-Gilbert (LLG) equation. This equation can be enhanced with additional terms that account for the torque acting on the magnetization, which is essential for MRAM functionality. This work is dedicated to the computational study and machine-learning assisted optimization of MRAM devices.  \nThe ﬁrst part of this work focuses on the study of the ﬁnite element method (FEM) based computation of the demagnetizing ﬁeld, a crucial contribution to the eﬀective ﬁeld originating from the long-range interaction of the magnetic moments. Computational solutions to remedy the challenges of the open-boundary problem are implemented, and their performance is evaluated.  \nThe second part of this thesis introduces novel computational approaches that combine reinforcement learning with micromagnetic simulations for MRAM device optimization. Traditionally, the application of current pulses to switch magnetoresistive memory cells relies on heuristics. However, this work demonstrates the eﬀectiveness of reinforcement learning in MRAM device control. By autonomously interacting with the simulation, a reinforcement learning agent discovers optimal switching pulse sequences and optimizes various objectives, eliminating the need for manual experimentation.  \ni  \nThis approach oﬀers a promising solution for enhancing the eﬃciency andeﬀectiveness of MRAM switching. The approach demonstrates that an agent trained on a ﬁxed set of parameters can eﬀectively transfer its knowledge of magnetization dynamics in the free layer to scenarios with varying environmental conditions. It is shown that over a wide range of material parameters, the agent is capable of achieving reversal of the free layer magnetization. Additionally, the approach is extended to SOT-assisted STT-MRAM, and it is shown that by modifying the rewarding strategy the focus of the learned pulse scheme can successfully be shifted towards diﬀerent objectives. Specifically, optimization for both fast magnetization reversal and energy-eﬃcient switching is performed. By condensing the dynamically applied pulses of the reinforcement learning agent, static pulse sequences are obtained that perform well across a wide parameter range.  \nKurzfassung  \nDie über Jahrzente hinweg anhaltende Verkleinerung von Halbleiterbauelementen hat neben einer erhöhten Integrationsdichte auch zu einer Zunahme des Stromverbrauchs im Standby-Modus aufgrund höherer Leckströme geführt. Bei der Lösung dieses Problems sind nichtﬂüchtige Speicher eine aussichtsreiche Technologie. Der magnetoresistive Direktzugriﬀsspeicher (MRAM) stellt aufgrund seiner einfachen Architektur und Kompatibilität mit der CMOS-Technologie eine vielversprechende nic","cbCaiiQ3aqDZrRKu","https://ap.wps.com/l/cbCaiiQ3aqDZrRKu","pdf",2814262,2,1,149,"English","en",105,"# Abstract\n## Finite-Element Method for Demagnetizing Field\n## Reinforcement Learning for MRAM Switching Optimization","[{\"question\":\"Why is MRAM considered a solution to standby power and leakage currents?\",\"answer\":\"Further down-scaling increases standby power consumption due to leakage currents. MRAM is highlighted as a promising non-volatile approach that avoids these issues while remaining compatible with CMOS technology.\"},{\"question\":\"How does the work model the magnetization dynamics in MRAM devices?\",\"answer\":\"Magnetization changes over time are described by solving the Landau-Lifshitz-Gilbert (LLG) equation, which is augmented with additional terms representing torque essential for MRAM functionality.\"},{\"question\":\"What role does reinforcement learning play in MRAM device optimization?\",\"answer\":\"A reinforcement learning agent interacts with micromagnetic simulations to autonomously learn optimal switching pulse sequences, removing reliance on heuristic tuning and manual experimentation. It also supports objective shifts and transfer across varying material parameters.\"}]","Machine Learning-Enhanced Numerical Modeling of Modern Magnetoresistive Memories - Dissertation | PDF",1786002805,375,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"machine-learning-enhanced-numerical-modeling-of-modern-magnetoresistive-memories-dissertation","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/machine-learning-enhanced-numerical-modeling-of-modern-magnetoresistive-memories-dissertation/128712/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-06",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is MRAM considered a solution to standby power and leakage currents?","Question",{"text":76,"@type":77},"Further down-scaling increases standby power consumption due to leakage currents. MRAM is highlighted as a promising non-volatile approach that avoids these issues while remaining compatible with CMOS technology.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the work model the magnetization dynamics in MRAM devices?",{"text":81,"@type":77},"Magnetization changes over time are described by solving the Landau-Lifshitz-Gilbert (LLG) equation, which is augmented with additional terms representing torque essential for MRAM functionality.",{"name":83,"@type":74,"acceptedAnswer":84},"What role does reinforcement learning play in MRAM device optimization?",{"text":85,"@type":77},"A reinforcement learning agent interacts with micromagnetic simulations to autonomously learn optimal switching pulse sequences, removing reliance on heuristic tuning and manual experimentation. It also supports objective shifts and transfer across varying material parameters.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]