[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117597-en":3,"doc-seo-117597-105":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},117597,962075114765,"Quinn","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Transfer learning and the early estimation of single-photon source quality using machine learning methods","Single-photon sources are essential for modern quantum technologies, yet manufacturing imperfections require experimental verification of emission purity, typically through interferometry. Such measurement is slow and expensive, driving research into inferring single-photon source quality from incomplete emission statistics. This study evaluates transfer learning for early estimation using eight datasets from an InGaAs/GaAs epitaxial quantum dot under varying excitation-laser intensity contexts. Five ML models (three linear, two ensemble) are trained on seven contexts and tested on the remaining one, comparing performance with standard least-squares fitting. Results show linear models can surpass baseline fitting in same-context tests, while transfer learning benefits are less guaranteed under context dissimilarity. Data augmentation supports the conclusion that transfer learning may still improve early estimation, and the work outlines future directions such as feature engineering and model adaptation.","PAPER • OPEN ACCESS  \nTransfer learning and the early estimation of single-photon source quality using machine learning methods  \nTo cite this article: David Jacob Kedziora et al 2025 Mach. Learn. : Sci. Technol. 6 025014  \nView the article online for updates and enhancements.  \nYou may also like  \n-Hyperparameter optimisation in deep learning from ensemble methods:  \napplications to proton structure  \nJuan Cruz-Martinez, Aron Jansen, Gijs van Oord et al.  \n-Enhancing friction stir-based techniques with machine learning: a comprehensive review  \nNoah E El-Zathry, Stephen Akinlabi, Wai Lok Woo et al.  \n-Wilsonian renormalization of neural network Gaussian processes  \nJessica N Howard, Ro Jefferson, Anindita Maiti et al.  \nThis content was downloaded from IP address [138.25.168.236](138.25.168.236) on 22/09/2025 at 03:47  \n Mach. Learn.: Sci. Technol. 6 (2025) 025014 [https://doi.org/10.1088/2632-2153/adc86f](https://doi.org/10.1088/2632-2153/adc86f)  \nPAPER  \nTransfer learning and the early estimation of single-photon source OPEN ACCESS quality using machine learning methods  \nRECEIVED  \n20 August 2024 David Jacob Kedziora1􀁂, Anna Musiał2􀁂, Wojciech Rudno-Rudzin´ski2􀁂 and Bogdan Gabrys1, ∗􀁂 REVISED10 March 2025 1 Complex Adaptive Systems Lab, University of Technology Sydney, Sydney, Australia  \n2 Department of Experimental Physics, Wroclaw University of Science and Technology, Wrocław, Poland A2CCEApElFO02PUBLICATION ∗ Author to whom any correspondence should be addressed.  \n[PUBLISHED](PUBLISHED E-mail: bogdan.gabrys@uts.edu.au)[ E-mail: bogdan.gabrys@uts.edu.au](PUBLISHED E-mail: bogdan.gabrys@uts.edu.au)  \n14 April 2025  \nKeywords: quantum dots, emission statistics, transfer learning, machine learning, data augmentation, quantum communication,   single-photon source quality  \nOriginal Content from this work may be used under the terms of the  \nCreative Commons Attribution 4 .0 licence.  \nAny further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.  \nAbstract  \nThe use of single-photon sources (SPSs) is central to numerous systems and devices proposed amidst a modern surge in quantum technology. However, manufacturing schemes remain imperfect, and single-photon emission purity must often be experimentally verified via interferometry. Such a process is typically slow and costly, which has motivated growing research into whether SPS quality can be more rapidly inferred from incomplete emission statistics. Hence, this study is a sequel to previous work that demonstrated significant uncertainty in the standard method of quality estimation, i.e. the least-squares fitting of a physically motivated function, and asks: can machine learning (ML) do better? The study leverages eight datasets obtained from measurements involving an exemplary quantum emitter, i.e. a single InGaAs/GaAs epitaxial quantum dot; these eight contexts predominantly vary in the intensity of the exciting laser. Specifically, via a form of ‘transfer learning’, five ML models, three linear and two ensemble-based, are trained on data from seven of the contexts and tested on the eighth. Validation metrics quickly reveal that even a linear regressor can outperform standard fitting when it is tested on the same contexts it was trained on, but the success of transfer learning is less assured, even though statistical analysis, made possible by data augmentation, suggests its superiority as an early estimator. Accordingly, the study concludes by discussing future strategies for grappling with the problem of SPS context dissimilarity, e.g. feature engineering and model adaptation.  \n1. Introduction  \nThe efficient design and fabrication of a reliable on-demand single-photon source (SPS) is a core research agenda within the field of modern quantum optics. Indeed, the ability to produce individual photons with precise control, leveraging their quantum nature, is a crucial enabler for various other techn","cbCaicMbFw9cF4ZH","https://ap.wps.com/l/cbCaicMbFw9cF4ZH","pdf",13984752,1,24,"English","en",105,"# Abstract\n# Introduction\n## Motivation and challenges in single-photon source quality control\n## Measurement of emission purity via g(2)(τ) and Hanbury Brown and Twiss interferometry\n## Research question and approach\n# Methods\n## Datasets and experimental contexts\n## Machine learning models and transfer learning protocol\n# Results and discussion\n## Comparison with standard least-squares fitting\n## Effects of data augmentation and context dissimilarity\n## Future strategies","[{\"question\":\"Why is early estimation of single-photon source quality important?\",\"answer\":\"Single-photon emission purity must be verified experimentally, usually using interferometry such as Hanbury Brown and Twiss measurements. These procedures are slow and costly, motivating faster inference from incomplete emission statistics.\"},{\"question\":\"How does the study evaluate transfer learning for SPS quality estimation?\",\"answer\":\"Eight datasets from an InGaAs/GaAs epitaxial quantum dot are used across differing excitation-laser intensity contexts. Five ML models are trained on seven contexts and tested on the eighth to assess early estimation performance.\"},{\"question\":\"What does the paper use as the key metric for SPS quality?\",\"answer\":\"The central marker is single-photon emission purity, experimentally tied to the probability of multi-photon emission. This is determined via g(2)(τ), commonly emphasizing g(2)(0) and thresholds that distinguish single-photon emission from multi-photon impurity.\"}]","Transfer learning and the early estimation of single-photon source quality using machine learning methods | PDF",1785677165,60,{"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},"transfer-learning-and-the-early-estimation-of-single-photon-source-quality-using-machine-learning-methods","",{"@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/transfer-learning-and-the-early-estimation-of-single-photon-source-quality-using-machine-learning-methods/117597/",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},"Why is early estimation of single-photon source quality important?","Question",{"text":75,"@type":76},"Single-photon emission purity must be verified experimentally, usually using interferometry such as Hanbury Brown and Twiss measurements. These procedures are slow and costly, motivating faster inference from incomplete emission statistics.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the study evaluate transfer learning for SPS quality estimation?",{"text":80,"@type":76},"Eight datasets from an InGaAs/GaAs epitaxial quantum dot are used across differing excitation-laser intensity contexts. Five ML models are trained on seven contexts and tested on the eighth to assess early estimation performance.",{"name":82,"@type":73,"acceptedAnswer":83},"What does the paper use as the key metric for SPS quality?",{"text":84,"@type":76},"The central marker is single-photon emission purity, experimentally tied to the probability of multi-photon emission. This is determined via g(2)(τ), commonly emphasizing g(2)(0) and thresholds that distinguish single-photon emission from multi-photon impurity.","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},[93,97,101,105,109,114,119,122,127,130,134],{"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":29,"slug":108},5,"Comic","comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"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"]