[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121931-en":3,"doc-seo-121931-105":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},121931,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Fast characterization of multiplexed single-electron pumps with machine learning - research article","An efficient machine learning–based automated framework accelerates tuning of single-electron pump devices into current quantization regimes. The approach uses sparse measurements driven by an iterative active learning algorithm to target gate-voltage regions rather than performing conventional parameter scans. Compared with scans, it reduces measurement points by about an order of magnitude and cuts the time to determine quantization errors by eightfold. Quantization errors are estimated via exponential extrapolation embedded in the algorithm, and robustness is demonstrated on 28 devices in a GaAs/AlGaAs multiplexer array, identifying candidates for parallel operation at shared gate voltages.","RESEARCH ARTICLE | SEPTEMBER 16 2024  \nFast characterization of multiplexed single-electron pumps with machine learning   \nSpecial Collection: Advances in Quantum Metrology  \nN. Schoinas  ; Y. Rath  ; S. Norimoto  ; W. Xie  ; P. See  ; J. P. Griffiths  ; C. Chen  ;  \nD. A. Ritchie  ; M. Kataoka  ; A. Rossi 􀀤  ; I. Rungger 􀀤   \nAppl. Phys. Lett. 125, 124001 (2024)  \n[https://doi.org/10.1063/5.0221387](https://doi.org/10.1063/5.0221387)  \n􀀪  \nView Online  \n􀀮  \nExport Citation  \n25 September 2024 08:45:31  \nApplied Physics Letters ARTICLE  \n[pubs.aip.org/aip/apl](pubs.aip.org/aip/apl)  \nFast characterization of multiplexed  \nsingle-electron pumps with machine learning   \nCite as: Appl. Phys. Lett. 125, 124001 (2024); doi: 10.1063/5.0221387  \nSubmitted: 31 May 2024 . Accepted: 12 August 2024 .  \nPublished Online: 16 September 2024  \nN. Schoinas,1  Y. Rath,1  S. Norimoto,1  W. Xie,1  P. See,1  J. P. Griffiths,2  C. Chen,2  D. A. Ritchie,2  M. Kataoka,1  A. Rossi,1,3,a)  and I. Rungger1,4,a)   \n\n| AFFILIATIONS\u003Cbr>1 National Physical Laboratory, Teddington TW11 0LW, United Kingdom\u003Cbr>2Cavendish Laboratory, University of Cambridge, J. J. Thomson Avenue, Cambridge CB3 0HE, United Kingdom 3 Department of Physics, SUPA, University of Strathclyde, Glasgow G4 0NG, United Kingdom\u003Cbr>4 Department of Computer Science, Royal Holloway, University of London, Egham TW20 0EX, United Kingdom\u003Cbr>Note: This paper is part of the APL Special Collection on Advances in Quantum Metrology.\u003Cbr>a)Authors to whom correspondence should be addressed: alessandro. rossi@npl.co. uk and [ivan.rungger@npl.co.uk](ivan.rungger@npl.co.uk) |\n| --- |\n| ABSTRACT\u003Cbr>We present an efficient machine learning based automated framework for the fast tuning of single-electron pump devices into current quantization regimes. It uses a sparse measurement approach based on an iterative active learning algorithm to take targeted measurements in the gate voltage parameter space. When compared to conventional parameter scans, our automated framework allows us to decrease the number of measurement points by about an order of magnitude. This corresponds to an eightfold decrease in the time required to determine quantization errors, which are estimated via an exponential extrapolation of the first current plateau embedded into the algorithm. We show the robustness of the framework by characterizing 28 individual devices arranged in a GaAs/AlGaAs multiplexer array, which we use to identify a subset of devices suitable for parallel operation at communal gate voltages. The method opens up the possibility to efficiently scale the characterization of such multiplexed devices to a large number of pumps.\u003Cbr>VC 2024 Author(s). All article content, except where otherwise noted, is licensed under a Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/4.0/](creativecommons.org/licenses/by/4.0/)). [https://doi.org/10.1063/5.0221387](https://doi.org/10.1063/5.0221387) |\n\nSingle-electron pumps are nanoscale devices that can produce quantized macroscopic electric currents by clocking the transfer of individual electrons to an external periodic drive.1–9 This device technology has been primarily developed to realize the practical implementation of the SI unit of current, the ampere, which, since 2019, is defined by the fixed value of the elementary charge, e.10–12 The overarching goal is the experimental realization of devices generating a quantized current according to the relationship I ¼ nef, where f is the periodic drive frequency and n is an integer multiple of electrons transferred in a cycle.  \nThe device operation requires a large degree of manual intervention to find the appropriate operation conditions in a large space of control parameters. With the increasing need of operating multiplexed devices in a parallel configuration to generate usefully large quantized currents,13–15 the manual tuning of control parameters for each device beco","cbCaiiEI3IXzi100","https://ap.wps.com/l/cbCaiiEI3IXzi100","pdf",3151666,1,7,"English","en",105,"# Abstract\n# Background and motivation\n# Machine learning framework\n## Sparse measurements with active learning\n## Exponential extrapolation for quantization errors\n# Experimental demonstration on a multiplexed device array","[{\"question\":\"How does the proposed machine learning framework speed up tuning of single-electron pumps?\",\"answer\":\"It uses sparse, targeted measurements obtained iteratively with an active learning algorithm in the gate-voltage parameter space, reducing the number of measurement points versus conventional scans.\"},{\"question\":\"How are quantization errors estimated in the framework?\",\"answer\":\"Quantization errors are determined using an exponential extrapolation procedure based on current plateau information obtained from targeted measurements.\"},{\"question\":\"How is the method validated experimentally?\",\"answer\":\"The framework characterizes 28 GaAs/AlGaAs pump devices arranged in a multiplexer array, enabling identification of a subset suitable for parallel operation at communal gate voltages.\"}]","Fast characterization of multiplexed single-electron pumps with machine learning - research article | PDF",1785807803,18,{"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},"fast-characterization-of-multiplexed-single-electron-pumps-with-machine-learning-research-article","",{"@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/fast-characterization-of-multiplexed-single-electron-pumps-with-machine-learning-research-article/121931/",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","2026-08-04",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},"How does the proposed machine learning framework speed up tuning of single-electron pumps?","Question",{"text":75,"@type":76},"It uses sparse, targeted measurements obtained iteratively with an active learning algorithm in the gate-voltage parameter space, reducing the number of measurement points versus conventional scans.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are quantization errors estimated in the framework?",{"text":80,"@type":76},"Quantization errors are determined using an exponential extrapolation procedure based on current plateau information obtained from targeted measurements.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the method validated experimentally?",{"text":84,"@type":76},"The framework characterizes 28 GaAs/AlGaAs pump devices arranged in a multiplexer array, enabling identification of a subset suitable for parallel operation at communal gate voltages.","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},[93,97,101,105,110,115,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"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"]