{"id":"https://openalex.org/W7163994527","doi":"https://doi.org/10.48550/arxiv.2606.07896","title":"Beyond the Thin-Layer Limit: Differentiable Volumetric Training for Visible-Range Diffractive Neural Networks","display_name":"Beyond the Thin-Layer Limit: Differentiable Volumetric Training for Visible-Range Diffractive Neural Networks","publication_year":2026,"publication_date":"2026-06-05","ids":{"openalex":"https://openalex.org/W7163994527","doi":"https://doi.org/10.48550/arxiv.2606.07896"},"language":null,"primary_location":{"id":"pmh:oai:figshare.com:article/32669760","is_oa":true,"landing_page_url":"https://figshare.com/articles/preprint/Beyond_the_Thin-Layer_Limit_Differentiable_Volumetric_Training_for_Visible-Range_Diffractive_Neural_Networks/32669760","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/preprint/Beyond_the_Thin-Layer_Limit_Differentiable_Volumetric_Training_for_Visible-Range_Diffractive_Neural_Networks/32669760","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138282669","display_name":"Dineth Jayakody","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jayakody, Dineth","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5083125733","display_name":"Dushan N. Wadduwage","orcid":"https://orcid.org/0000-0002-0689-9454"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wadduwage, Dushan N.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.9860000014305115,"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":0.9860000014305115,"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/T10245","display_name":"Metamaterials and Metasurfaces Applications","score":0.004100000020116568,"subfield":{"id":"https://openalex.org/subfields/2504","display_name":"Electronic, Optical and Magnetic Materials"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10299","display_name":"Photonic and Optical Devices","score":0.002099999925121665,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.6029999852180481},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5200999975204468},{"id":"https://openalex.org/keywords/terahertz-radiation","display_name":"Terahertz radiation","score":0.5160999894142151},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4900999963283539},{"id":"https://openalex.org/keywords/diffraction","display_name":"Diffraction","score":0.48069998621940613},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4645000100135803},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.4586000144481659},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4490000009536743},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.3698999881744385}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6029999852180481},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5995000004768372},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5200999975204468},{"id":"https://openalex.org/C107816215","wikidata":"https://www.wikidata.org/wiki/Q647887","display_name":"Terahertz radiation","level":2,"score":0.5160999894142151},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4900999963283539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48420000076293945},{"id":"https://openalex.org/C207114421","wikidata":"https://www.wikidata.org/wiki/Q133900","display_name":"Diffraction","level":2,"score":0.48069998621940613},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.4699000120162964},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4645000100135803},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.4586000144481659},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4490000009536743},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C6260449","wikidata":"https://www.wikidata.org/wiki/Q41364","display_name":"Wavelength","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.34450000524520874},{"id":"https://openalex.org/C184880428","wikidata":"https://www.wikidata.org/wiki/Q1417308","display_name":"Finite-difference time-domain method","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C187590223","wikidata":"https://www.wikidata.org/wiki/Q527628","display_name":"Holography","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31369999051094055},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31139999628067017},{"id":"https://openalex.org/C50282329","wikidata":"https://www.wikidata.org/wiki/Q2286895","display_name":"Fresnel diffraction","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.272599995136261},{"id":"https://openalex.org/C138211643","wikidata":"https://www.wikidata.org/wiki/Q675211","display_name":"Bent molecular geometry","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C81793267","wikidata":"https://www.wikidata.org/wiki/Q7180962","display_name":"Phase retrieval","level":3,"score":0.25940001010894775},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C166689943","wikidata":"https://www.wikidata.org/wiki/Q850283","display_name":"Interferometry","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C9395851","wikidata":"https://www.wikidata.org/wiki/Q177929","display_name":"Stack (abstract data type)","level":2,"score":0.25049999356269836},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.25}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:figshare.com:article/32669760","is_oa":true,"landing_page_url":"https://figshare.com/articles/preprint/Beyond_the_Thin-Layer_Limit_Differentiable_Volumetric_Training_for_Visible-Range_Diffractive_Neural_Networks/32669760","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"doi:10.48550/arxiv.2606.07896","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.07896","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/32669760","is_oa":true,"landing_page_url":"https://figshare.com/articles/preprint/Beyond_the_Thin-Layer_Limit_Differentiable_Volumetric_Training_for_Visible-Range_Diffractive_Neural_Networks/32669760","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffractive":[0],"deep":[1],"neural":[2],"networks":[3],"(D2NNs)":[4],"promise":[5],"miniaturized,":[6],"power-efficient,":[7],"light-speed":[8],"optical":[9,208],"front-ends":[10],"for":[11],"machine":[12],"vision,":[13],"yet":[14],"the":[15,21,33,46,72,76,99,108,157,167,181],"most":[16],"mature":[17],"demonstrations":[18],"remain":[19,66],"in":[20,166],"terahertz":[22,64],"regime,":[23],"built":[24],"from":[25,191],"readily":[26],"fabricated":[27],"millimeter-scale":[28],"neurons.":[29],"Translating":[30],"D2NNs":[31,61],"to":[32,193],"visible":[34,116],"range,":[35],"where":[36],"nearly":[37,80],"all":[38,81],"vision":[39],"pipelines":[40],"operate,":[41],"was":[42],"long":[43],"blamed":[44],"on":[45],"difficulty":[47],"of":[48,68,98],"fabricating":[49],"nanoscale":[50],"neurons;":[51],"but":[52,106],"even":[53],"after":[54],"recent":[55],"advances":[56],"removed":[57],"that":[58,123,141],"barrier,":[59],"visible-range":[60],"matching":[62],"their":[63],"counterparts":[65],"out":[67],"reach.":[69],"We":[70],"identify":[71],"true":[73],"obstacle":[74],"as":[75,89,102,145],"thin-layer":[77],"approximation":[78],"underlying":[79],"D2NN":[82],"training,":[83,155],"which":[84],"treats":[85],"each":[86,143],"diffractive":[87,213],"layer":[88,140,199],"an":[90],"infinitely":[91],"thin":[92],"mask.":[93],"It":[94],"fails":[95],"not":[96],"because":[97,107],"short":[100],"wavelength,":[101],"is":[103],"commonly":[104],"assumed,":[105],"low-refractive-index":[109],"materials":[110],"(n":[111],"approximately":[112],"1.3-1.5)":[113],"used":[114],"at":[115],"wavelengths":[117],"require":[118],"relief":[119],"structures":[120],"thick":[121],"enough":[122],"intra-layer":[124],"diffraction":[125],"and":[126,149,172,175,184,211],"phase":[127],"accumulation":[128],"become":[129],"significant.":[130],"To":[131],"overcome":[132],"this,":[133],"we":[134],"introduce":[135],"a":[136,146,202],"differentiable":[137],"beam-propagation":[138],"($\\partial$BPM)":[139],"models":[142],"element":[144],"finite-thickness":[147],"volume":[148],"propagates":[150],"light":[151],"through":[152],"it":[153],"during":[154],"keeping":[156],"fabrication-compatible":[158],"height":[159],"map":[160],"end-to-end":[161],"trainable":[162],"without":[163,195],"full-wave":[164,185],"simulation":[165],"loop.":[168],"Across":[169],"MNIST,":[170],"Fashion-MNIST,":[171],"CIFAR-100":[173],"classification":[174,189],"imaging,":[176],"$\\partial$BPM":[177,198],"training":[178],"substantially":[179],"reduces":[180],"design-to-device":[182],"mismatch,":[183],"FDTD":[186],"validation":[187],"raises":[188],"accuracy":[190],"50%":[192],"90%":[194],"re-optimization.":[196],"The":[197],"thus":[200],"offers":[201],"scalable,":[203],"physics-aware":[204],"bridge":[205],"between":[206],"efficient":[207],"neural-network":[209],"optimization":[210],"fabrication-consistent":[212],"design.":[214]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-06-10T00:00:00"}