{"id":"https://openalex.org/W7151053718","doi":"https://doi.org/10.48550/arxiv.2604.02429","title":"Photonic convolutional neural network with pre-trained in-situ training","display_name":"Photonic convolutional neural network with pre-trained in-situ training","publication_year":2026,"publication_date":"2026-04-02","ids":{"openalex":"https://openalex.org/W7151053718","doi":"https://doi.org/10.48550/arxiv.2604.02429"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.02429","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.02429","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.02429","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133004156","display_name":"Saurabh Ranjan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ranjan, Saurabh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089097573","display_name":"Sonika Thakral","orcid":"https://orcid.org/0000-0003-1173-1100"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thakral, Sonika","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036317848","display_name":"Amit Sehgal","orcid":"https://orcid.org/0000-0002-1578-8131"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sehgal, Amit","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10299","display_name":"Photonic and Optical Devices","score":0.006500000134110451,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10232","display_name":"Optical Network Technologies","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.6952999830245972},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5878000259399414},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5195000171661377},{"id":"https://openalex.org/keywords/photonics","display_name":"Photonics","score":0.5194000005722046},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.38280001282691956},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.38190001249313354},{"id":"https://openalex.org/keywords/multiplexing","display_name":"Multiplexing","score":0.3727000057697296},{"id":"https://openalex.org/keywords/optical-computing","display_name":"Optical computing","score":0.36410000920295715},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3637000024318695}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7572000026702881},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.6952999830245972},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5878000259399414},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5195000171661377},{"id":"https://openalex.org/C20788544","wikidata":"https://www.wikidata.org/wiki/Q467054","display_name":"Photonics","level":2,"score":0.5194000005722046},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.4246000051498413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4212999939918518},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.41440001130104065},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C19275194","wikidata":"https://www.wikidata.org/wiki/Q222903","display_name":"Multiplexing","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C148204187","wikidata":"https://www.wikidata.org/wiki/Q176541","display_name":"Optical computing","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3637000024318695},{"id":"https://openalex.org/C32900221","wikidata":"https://www.wikidata.org/wiki/Q181365","display_name":"Dot product","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C119423029","wikidata":"https://www.wikidata.org/wiki/Q3749103","display_name":"Silicon photonics","level":3,"score":0.30559998750686646},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C80469333","wikidata":"https://www.wikidata.org/wiki/Q189088","display_name":"Von Neumann architecture","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C166689943","wikidata":"https://www.wikidata.org/wiki/Q850283","display_name":"Interferometry","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.26030001044273376},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25690001249313354},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25369998812675476},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.02429","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.02429","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.02429","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.02429","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8997513055801392}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Photonic":[0],"computing":[1,4],"is":[2,36,116],"a":[3,54,142,147],"paradigm":[5],"which":[6,122],"have":[7],"great":[8],"potential":[9],"to":[10,87,91,172,186],"overcome":[11,131],"the":[12,68,132],"energy":[13,190],"bottlenecks":[14],"of":[15,27,134],"electronic":[16,194],"von":[17],"Neumann":[18],"architecture.":[19],"Throughput":[20],"and":[21,42,52,89,108,183],"power":[22],"consumption":[23],"are":[24],"fundamental":[25],"limitations":[26],"Complementary-metal-oxide-semiconductor":[28],"(CMOS)":[29],"chips,":[30],"therefore":[31],"convolutional":[32,57],"neural":[33,58],"network":[34,59],"(CNN)":[35],"revolutionising":[37],"machine":[38],"learning,":[39],"computer":[40],"vision":[41],"other":[43],"image":[44,64],"based":[45],"applications.":[46],"In":[47],"this":[48],"work,":[49],"we":[50,140],"propose":[51],"validate":[53],"fully":[55,117],"photonic":[56],"(PCNN)":[60],"that":[61,79],"performs":[62],"MNIST":[63],"classification":[65],"entirely":[66],"in":[67],"optical":[69,86,92],"domain,":[70],"achieving":[71],"94":[72],"percent":[73,177],"test":[74],"accuracy.":[75],"Unlike":[76],"existing":[77],"architectures":[78],"rely":[80],"on":[81,119],"frequent":[82],"in-between":[83],"conversions":[84],"from":[85],"electrical":[88,128],"back":[90],"(O/E/O),":[93],"our":[94],"system":[95],"maintains":[96],"coherent":[97],"processing":[98],"utilizing":[99],"Mach-Zehnder":[100],"interferometer":[101],"(MZI)":[102],"meshes,":[103],"wavelength-division":[104],"multiplexed":[105],"(WDM)":[106],"pooling,":[107],"microring":[109],"resonator-based":[110],"nonlinearities.":[111],"The":[112],"max":[113],"pooling":[114],"unit":[115],"implemented":[118],"silicon":[120],"photonics,":[121],"does":[123],"not":[124],"require":[125],"opto-electrical":[126],"or":[127],"conversions.":[129],"To":[130],"challenges":[133],"training":[135,144],"physical":[136],"phase":[137],"shifter":[138],"parameters,":[139],"introduce":[141],"hybrid":[143],"methodology":[145],"deploying":[146],"mathematically":[148],"exact":[149],"differentiable":[150],"digital":[151],"twin":[152],"for":[153,196],"ex-situ":[154],"backpropagation,":[155],"followed":[156],"by":[157],"in-situ":[158],"fine-tuning":[159],"via":[160],"Simultaneous":[161],"Perturbation":[162],"Stochastic":[163],"Approximation":[164],"(SPSA)":[165],"algorithm.":[166],"Our":[167],"evaluation":[168],"demonstrates":[169],"significant":[170],"robustness":[171],"thermal":[173],"crosstalk":[174],"(only":[175],"0.43":[176],"accuracy":[178],"degradation":[179],"at":[180],"severe":[181],"coupling)":[182],"achieves":[184],"100":[185],"242":[187],"times":[188],"better":[189],"efficiency":[191],"than":[192],"state-of-the-art":[193],"GPUs":[195],"single-image":[197],"inference.":[198]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-07T00:00:00"}