[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126895-en":3,"doc-seo-126895-105":30,"detail-sidebar-cat-0-en-105":91},{"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":11,"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":29},126895,2336474466712,"Maeve","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Machine Learning-Assisted Device Circuit Co-optimization - A Case Study on Inverter - Abstract","This study presents a machine learning-assisted co-optimization method that jointly improves device and circuit parameters for a basic CMOS inverter. Voltage transfer and switching behaviors are analyzed under distinct pulse conditions (140 ns and 100 ps) to capture ON/OFF state performance. Actor-critic neural networks guide mixed-mode simulations combining TCAD and SPICE outputs, optimizing area factor, doping concentration, capacitance, and device dimensions. Compared with manual design, the co-optimized solution improves multiple figures of merit including propagation delay and overshoot.","Xue, L., Dixit, A., Kumar, N., Georgiev, V. and Liu, B. (2024) Machine learning-assisted device circuit co-optimization: A case study on inverter. IEEE Transactions on Electron Devices, 71(12), pp. 7256- 7262. (doi:  10.1109/TED.2024.3476231)  \nThis is the author version of the work deposited here under a Creative Commons license: [https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)  \nCopyright © 2024 IEEE  \nThis is the author version of the work. There may be differences between this version and the published version. You are advised to consult the published version if you wish to cite from it:  \n[https://doi.org/10.1109/TED.2024.3476231](https://doi.org/10.1109/TED.2024.3476231)  \n[https://eprints.gla.ac.uk/337933/](https://eprints.gla.ac.uk/337933/)  \nDeposited on 07 October 2024  \nEnlighten – Research publications by members of the University of Glasgow  \n[http://eprints.gla.ac.uk](http://eprints.gla.ac.uk)  \nGENERIC COLORIZED JOURNAL, VOL. XX, NO. XX, XXXX 2024 1  \nMachine Learning-Assisted Device Circuit Co-optimization: A Case Study on Inverter  \nLiyuan Xue, Student Member, IEEE , Ankit Dixit, Member, IEEE , Naveen Kumar, Member, IEEE, Vihar Georgiev, Senior Member, IEEE , and Bo Liu, Senior Member, IEEE  \nAbstract—This study demonstrates a machine learningassisted device circuit co-optimization technique. A basic CMOS inverter cell is employed to demonstrate this proof of concept. The voltage transfer and the switching characteristics are examined to observe the ON- and OFF-state behavior while applying two short square pulses of 140 nsand 100 ps, respectively. By applying the proposed machine learning-based optimization method using the actor and critic neural networks, the mixed-mode simulation (i.e., TCAD and SPICE) output towards the desired behavior of the circuit, and parameters including area factor, doping concentration, capacitance value, and width and length of the device, are optimized. Compared to the manual design case, the co-optimized design surpasses several figures of merit, such as propagation delay and overshoot, which pave the way for future research on more complex circuit design challenges.  \nIndex Terms—CMOS Inverter, Machine Learning, Actorcritic-based Optimization, TCAD, Mixed-Mode Simulations  \nI. INTRODUCTION  \nIn the current era of semiconductor technology, numerous advancements are taking place at the device level, includingthe development of FinFET, nanosheet [1], and gate-all-around transistors [2] . These devices empower circuit engineers to design intricate circuits, such as memory and processors, with higher efficiency in terms of reduced power consumption and enhanced processing speed. However, the performance of these circuits relies not only on the precise adjustment of external passive components, such as resistors and capacitors [3], but also, predominantly, on the physical characteristics of the device. These characteristics include the width and length of the device, and also the process and material of the device, such asthe doping concentration in the channel region of CMOS. The manual tuning procedure for determining the accurate values of these parameters is a challenging task involving substantial  \nThis work was supported in part by the Engineering and Physical Sciences Research Council (EPSRC) under Grant EP/V048341/1 and EPSRC IAA award EP/X5257161/1 . The review of this article was arranged by Editor XXXXX (Corresponding author: Ankit Dixit, Liyuan Xue.) Liyuan Xue, Ankit Dixit, Naveen Kumar, Vihar Georgiev, and Bo Liu are with James Watt School of Engineering, University of Glasgow, G12 8LT Glasgow, U.K.(e-mail: [l.xue.1@research.gla.ac.uk](l.xue.1@research.gla.ac.uk), [ankit.dixit@glasgow.ac.uk](ankit.dixit@glasgow.ac.uk), [naveen.kumar@glasgow.ac.uk](naveen.kumar@glasgow.ac.uk), [vihar.georgiev@glasgow.ac.uk](vihar.georgiev@glasgow.ac.uk) and [bo.liu@glasgow.ac.uk](bo.liu@glasgow.ac.uk)).  \nLiyuan Xue and Bo Liu are with the AI","cbCaieVHF5nTpzcP","https://ap.wps.com/l/cbCaieVHF5nTpzcP","pdf",1512150,2,1,"English","en",105,"# Introduction\n## Device-level advances and design dependencies\n## Challenges in manual parameter tuning and simulation cost\n# Proposed ML-assisted co-optimization approach\n## Joint optimization workflow for device and circuit parameters","[{\"question\":\"What does the proposed machine learning-assisted method optimize in the CMOS inverter?\",\"answer\":\"It co-optimizes device and circuit parameters simultaneously, using performance modeled directly at the circuit level to guide the search toward the desired inverter behavior.\"},{\"question\":\"How are the inverter switching characteristics evaluated in the study?\",\"answer\":\"The study examines voltage transfer and switching characteristics by applying two short square pulses, 140 ns and 100 ps, to observe ON- and OFF-state behavior.\"},{\"question\":\"What simulation and optimization components are used to drive the design improvements?\",\"answer\":\"The method uses actor and critic neural networks and relies on mixed-mode simulation outputs that combine TCAD and SPICE results to optimize parameters such as area factor, doping concentration, capacitance, and device dimensions.\"}]","Machine Learning-Assisted Device Circuit Co-optimization - A Case Study on Inverter - Abstract | PDF",1785935475,20,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-assisted-device-circuit-co-optimization-a-case-study-on-inverter-abstract","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/machine-learning-assisted-device-circuit-co-optimization-a-case-study-on-inverter-abstract/126895/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What does the proposed machine learning-assisted method optimize in the CMOS inverter?","Question",{"text":75,"@type":76},"It co-optimizes device and circuit parameters simultaneously, using performance modeled directly at the circuit level to guide the search toward the desired inverter behavior.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are the inverter switching characteristics evaluated in the study?",{"text":80,"@type":76},"The study examines voltage transfer and switching characteristics by applying two short square pulses, 140 ns and 100 ps, to observe ON- and OFF-state behavior.",{"name":82,"@type":73,"acceptedAnswer":83},"What simulation and optimization components are used to drive the design improvements?",{"text":84,"@type":76},"The method uses actor and critic neural networks and relies on mixed-mode simulation outputs that combine TCAD and SPICE results to optimize parameters such as area factor, doping concentration, capacitance, and device dimensions.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":29,"slug":126},9,"Religion & Spirituality","religion-spirituality",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":29,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]