[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120978-en":3,"doc-seo-120978-105":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},120978,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","Identifying topology of leaky photonic lattices with machine learning","The work applies machine learning to classify topological phases in leaky photonic lattices using limited measurements. A bulk-intensity-only strategy is introduced, avoiding phase retrieval and enabling reliable inference from output intensity distributions. A fully connected neural network determines topological properties in dimerized waveguide arrays with leaky channels after propagation of a localized excitation at a finite distance, designed to mirror realistic experimental conditions. The study also targets effects of disorder, alignment imperfections, and restricted observables on classification and clustering performance.","arXiv :2308 . 14407v1 [physics .optics] 28 Aug 2023  \nIdentifying topology of leaky photonic lattices with machine learning  \nEkaterina O. Smolina, 1 Lev A. Smirnov, 1 Daniel Leykam,2 Franco Nori,3, 4, 5 and Daria A. Smirnova3, 6  \n1 Department of Control Theory, Nizhny Novgorod State University,  \nGagarin Av. 23, Nizhny Novgorod, 603950 Russia  \n2 Centre for Quantum Technologies, National University of Singapore, 3 Science Drive 2, Singapore 117543  \n3 Theoretical Quantum Physics Laboratory, Cluster for Pioneering Research, RIKEN, Wakoshi, Saitama 351-0198, Japan  \n4 Center for Quantum Computing (RQC), RIKEN, Wako-shi, Saitama 351-0198, Japan  \n5 Physics Department, University of Michigan, Ann Arbor, MI 48109-1040, USA  \n6 Research School of Physics, Australian National University, Canberra, ACT 2601, Australia  \nWe show how machine learning techniques can be applied for the classification of topological phases in leaky photonic lattices using limited measurement data. We propose an approach based solely on bulk intensity measurements, thus exempt from the need for complicated phase retrieval procedures. In particular, we design a fully connected neural network that accurately determines topological properties from the output intensity distribution in dimerized waveguide arrays with leaky channels, after propagation of a spatially localized initial excitation at a finite distance, in a setting that closely emulates realistic experimental conditions.  \nI. INTRODUCTION  \nMachine learning holds great promise for solving a variety of problems in nanophotonics. Rather than attempting to model the system of interest exactly from first principles (e.g., by solving Maxwell’s equations), machine learning techniques aim to discover or reproduce key features of a system by optimizing parametrized models using a set of training data [1] . A trained model can often predict the properties of a device faster than conventional simulation techniques [2, 3] . Machine learning can also be used to solve the inverse problems of how to design a nanophotonic structure with desired functionalities, and how to reconstruct the parameters of a device using indirect measurements [4–8] . The latter is particularly important for nanophotonic devices, since structural parameters may differ substantially from the nominal design due to fabrication imperfections.  \nRecently developed topological photonic systems provide a useful testbed for better understanding the capabilities and limitations of machine learning approaches in nanophotonics [9, 10] . Topological photonic structures host robust edge states which are protected against certain classes of fabrication imperfections. This robustness is explained by the bulkboundary correspondence, which relates the existence of localized boundary modes to nonlocal topological invariants expressed as integrals of a connection or curvature of the bulk modes [11] . While the direct measurement of a topological invariant entails the reconstruction of both the intensity and phase profiles of the bulk modes of a structure, machine learning models can perform supervised classification of topological phases using a limited set of observables [9] .  \nIn general, the performance of machine learning depends on both the quality and quantity of the data used to train the model. Supervised learning approaches, such as deep neural networks, typically require a huge quantity of labelled training data, which may be hard to come by. This has motivated recent interest in the use of unsupervised learning techniques such as manifold learning, which do not re-  \nquire labelled training data to distinguish topological phases [12–16] . Broadly speaking, these techniques are sensitive to sharp changes to observables that occur in the vicinity of topological phase transition points, and thus perform best when one has access to measurements from a large set of different model parameters, which is most feasible when the parameter controlling ","cbCaigkU8oIH7cZS","https://ap.wps.com/l/cbCaigkU8oIH7cZS","pdf",3745891,1,9,"English","en",105,"# Introduction\n## Motivation: machine learning in nanophotonics\n## Topological photonic systems and limited observables\n## Data quality, feature selection, and uncertainties\n## Aim and scope of the study","[{\"question\":\"How does the approach classify topological phases in leaky photonic lattices?\",\"answer\":\"It uses machine learning to classify topological phases from bulk output intensity distributions, avoiding the need to reconstruct both intensity and phase profiles.\"},{\"question\":\"What measurements does the method require?\",\"answer\":\"The method relies solely on bulk intensity measurements, so it does not require complicated phase retrieval procedures.\"},{\"question\":\"Which practical experimental challenges does the study address?\",\"answer\":\"It investigates how disorder, imperfect alignment, and access to a limited set of output observables affect classification and clustering of topological phases.\"}]","Identifying topology of leaky photonic lattices with machine learning | PDF",1785733149,23,{"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},"identifying-topology-of-leaky-photonic-lattices-with-machine-learning","",{"@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/identifying-topology-of-leaky-photonic-lattices-with-machine-learning/120978/",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","2026-08-03",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 approach classify topological phases in leaky photonic lattices?","Question",{"text":75,"@type":76},"It uses machine learning to classify topological phases from bulk output intensity distributions, avoiding the need to reconstruct both intensity and phase profiles.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What measurements does the method require?",{"text":80,"@type":76},"The method relies solely on bulk intensity measurements, so it does not require complicated phase retrieval procedures.",{"name":82,"@type":73,"acceptedAnswer":83},"Which practical experimental challenges does the study address?",{"text":84,"@type":76},"It investigates how disorder, imperfect alignment, and access to a limited set of output observables affect classification and clustering of topological phases.","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},[93,97,101,105,110,115,120,123,127,130,134],{"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":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":21,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"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"]