[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117622-en":3,"doc-seo-117622-105":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":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":29},117622,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Machine Learning Driven Global Optimisation Framework for Analog Circuit Design","Proposes a machine learning-driven optimisation framework for analog circuit design that builds global offline surrogate models using circuit parameters as inputs within the design space. The surrogates guide optimisation toward optimal designs, enabling faster convergence and fewer SPICE simulations. Multi-layer perceptron and random forest regressors predict circuit specifications, while MLP classifiers estimate each transistor’s saturation condition. Validation uses three circuit topologies: bandgap reference, folded cascode operational amplifier, and two-stage operational amplifier.","Machine Learning Driven Global Optimisation Framework for Analog Circuit Design  \nRia Rashida,∗, Komala Krishnaa , Clint Pazhayidam Georgeb , Nandakumar Nambatha  \na School of Electrical Sciences, Indian Institute of Technology Goa, Ponda, 403401, Goa, India b School of Mathematics and Computer Science, Indian Institute of Technology Goa, Ponda, 403401, Goa, India  \nAbstract  \nWe propose a machine learning-driven optimisation framework for analog circuit design in this paper. Machine learning based global o􀀏ine surrogate models, with the circuit design parameters as the input, are built in the design space for the analog circuits under study and is used to guide the optimisation algorithm towards an optimal circuit design, resulting in faster convergence and reduced number of spice simulations. Multi-layer perceptron and random forest regressors are employed to predict the required design speci􀀌cations of the analog circuit. Multi-layer perceptronclassi􀀌ers are used to predict the saturation condition of each transistor in the circuit. We validate the proposed framework using three circuit topologies–a bandgap reference, a folded cascode operational ampli􀀌er, and a two-stage operational ampli􀀌er. The simulation results show better optimum values and lower standard deviations for 􀀌tness functions after convergence, with a reduction in spice calls by 56%, 59%, and 83% when compared with standard approaches in the three test cases considered in the study.  \nKeywords:  \nAnalog circuit design, automated sizing, evolutionary algorithm, o􀀏ine surrogate model, machine learning, neural networks, random forests, supervised learning  \n1. Introduction  \nThe present-day electronic industry uses more and more integrated analog and digital blocks on monolithic mixedsignal system-on-a-chip (SoC) . The main bottleneck to the rapid development cycles of SoCs is the lack of automation in the analog design process. This is primarily because of the complexities present in analog circuit design [1] . Digital circuit design, on the other hand, is heavily automated. This necessitates the development of new, robust analog design automation tools [2, 3] .  \nMultiple studies have been reported for the automated sizing of analog circuits [4, 5, 6, 7], which are typically classi􀀌ed into equation-based and simulation-based [8, 9] . In equation-based approaches [9, 10], analytical expressions are used to model the di􀀋erent circuit speci􀀌cations with respect to design parameters. Since the models of the state-of-the-art transistors are highly complex, developing an accurate circuit model becomes quite challenging. Various higher-order e􀀋ects are thus ignored while framing the required equations for circuit performance evaluation. Asa result, the optimal design achieved by these methods is often found to be inadequate.  \nIn simulation-based approaches [11, 12, 13, 14, 15, 16], optimisation algorithms 􀀌nd the design parameters of the  \nconsidered analog circuit to meet the required speci􀀌cations with the help of any electronic design automation (EDA) tool, including spice [17] . Combined with the ability of spice simulations to predict the performance metrics of any analog circuits, this method can be applied to any complex analog circuit without needing to develop accurate mathematical models of the circuit under study. Different methods have been reported in the literature with various simulation-based techniques for analog circuit optimisation. Self-adaptive multiple starting point optimisations [18], simulated annealing [19, 20], Bayesian optimisation [21, 22], arti􀀌cial intelligence-based approach [23], shrinking circles technique [24], machine learningbased optimisation methods [25, 26], and evolutionary algorithms [27, 28, 29, 30] are a few methods reported for analog circuit design optimisation. A variety of evolutionary global optimisation algorithms such as di􀀋erential evolution (DE) [31], genetic algorithm (GA) [32, 33], arti􀀌cial bee colony (ABC) a","cbCaie6vbB842Lyo","https://ap.wps.com/l/cbCaie6vbB842Lyo","pdf",303992,1,14,"English","en",105,"# Introduction\n## Analog design automation bottlenecks\n## Automated sizing approaches: equation-based vs simulation-based\n## Simulation-based optimisation methods and evolutionary algorithms\n## Surrogate models for reducing SPICE simulations","[{\"question\":\"What problem does the proposed framework address in analog circuit design?\",\"answer\":\"It targets the lack of automation in analog design, which slows electronic system-on-chip development due to the complexity of analog circuit design.\"},{\"question\":\"How do the surrogate models improve the optimisation process?\",\"answer\":\"Offline machine learning surrogate models replace many direct SPICE evaluations during optimisation, guiding the algorithm toward optimal designs with faster convergence and fewer simulations.\"},{\"question\":\"Which circuit examples are used to validate the framework?\",\"answer\":\"The framework is validated on three topologies: a bandgap reference, a folded cascode operational amplifier, and a two-stage operational amplifier.\"}]","Machine Learning Driven Global Optimisation Framework for Analog Circuit Design | PDF",1785677333,35,{"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-driven-global-optimisation-framework-for-analog-circuit-design","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-driven-global-optimisation-framework-for-analog-circuit-design/117622/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the proposed framework address in analog circuit design?","Question",{"text":75,"@type":76},"It targets the lack of automation in analog design, which slows electronic system-on-chip development due to the complexity of analog circuit design.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How do the surrogate models improve the optimisation process?",{"text":80,"@type":76},"Offline machine learning surrogate models replace many direct SPICE evaluations during optimisation, guiding the algorithm toward optimal designs with faster convergence and fewer simulations.",{"name":82,"@type":73,"acceptedAnswer":83},"Which circuit examples are used to validate the framework?",{"text":84,"@type":76},"The framework is validated on three topologies: a bandgap reference, a folded cascode operational amplifier, and a two-stage operational amplifier.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"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":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]