Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304587443> ?p ?o ?g. }
- W4304587443 endingPage "2846" @default.
- W4304587443 startingPage "2846" @default.
- W4304587443 abstract "Modern machine-learning applications require huge artificial networks demanding computational power and memory. Light-based platforms promise ultrafast and energy-efficient hardware, which may help realize next-generation data processing devices. However, current photonic networks are limited by the number of input-output nodes that can be processed in a single shot. This restricted network capacity prevents their application to relevant large-scale problems such as natural language processing. Here, we realize a photonic processor for supervised learning with a capacity exceeding <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML display=inline id=m1> <mml:mrow> <mml:mn>1.5</mml:mn> <mml:mo>×</mml:mo> <mml:msup> <mml:mrow> <mml:mn>10</mml:mn> </mml:mrow> <mml:mrow> <mml:mn>10</mml:mn> </mml:mrow> </mml:msup> </mml:mrow> </mml:math> optical nodes, more than one order of magnitude larger than any previous implementation, which enables photonic large-scale text encoding and classification. By exploiting the full three-dimensional structure of the optical field propagating in free space, we overcome the interpolation threshold and reach the over-parameterized region of machine learning, a condition that allows high-performance sentiment analysis with a minimal fraction of training points. Our results provide a novel solution to scale up light-driven computing and open the route to photonic natural language processing." @default.
- W4304587443 created "2022-10-12" @default.
- W4304587443 creator A5013164931 @default.
- W4304587443 creator A5041199457 @default.
- W4304587443 creator A5080967998 @default.
- W4304587443 creator A5083885492 @default.
- W4304587443 date "2022-11-28" @default.
- W4304587443 modified "2023-09-30" @default.
- W4304587443 title "Large-scale photonic natural language processing" @default.
- W4304587443 cites W1965702053 @default.
- W4304587443 cites W2026131661 @default.
- W4304587443 cites W2036451492 @default.
- W4304587443 cites W2170993585 @default.
- W4304587443 cites W2256527444 @default.
- W4304587443 cites W2587524409 @default.
- W4304587443 cites W2613833839 @default.
- W4304587443 cites W2739588406 @default.
- W4304587443 cites W2752849906 @default.
- W4304587443 cites W2770947648 @default.
- W4304587443 cites W2798701005 @default.
- W4304587443 cites W2923873769 @default.
- W4304587443 cites W2944119451 @default.
- W4304587443 cites W2951042832 @default.
- W4304587443 cites W2962632550 @default.
- W4304587443 cites W2963417959 @default.
- W4304587443 cites W2963518130 @default.
- W4304587443 cites W2975126970 @default.
- W4304587443 cites W2986967681 @default.
- W4304587443 cites W2995189065 @default.
- W4304587443 cites W3002979339 @default.
- W4304587443 cites W3014851020 @default.
- W4304587443 cites W3031084598 @default.
- W4304587443 cites W3037032032 @default.
- W4304587443 cites W3083720136 @default.
- W4304587443 cites W3096274078 @default.
- W4304587443 cites W3099266033 @default.
- W4304587443 cites W3107308400 @default.
- W4304587443 cites W3118265437 @default.
- W4304587443 cites W3119901359 @default.
- W4304587443 cites W3120165331 @default.
- W4304587443 cites W3121141908 @default.
- W4304587443 cites W3128451613 @default.
- W4304587443 cites W3130293128 @default.
- W4304587443 cites W3153257371 @default.
- W4304587443 cites W3156357868 @default.
- W4304587443 cites W3159854664 @default.
- W4304587443 cites W3164870498 @default.
- W4304587443 cites W3172995164 @default.
- W4304587443 cites W3195686263 @default.
- W4304587443 cites W3196045945 @default.
- W4304587443 cites W3196262621 @default.
- W4304587443 cites W3202971499 @default.
- W4304587443 cites W3204998121 @default.
- W4304587443 cites W3210004558 @default.
- W4304587443 cites W4200169792 @default.
- W4304587443 cites W4210305137 @default.
- W4304587443 doi "https://doi.org/10.1364/prj.472932" @default.
- W4304587443 hasPublicationYear "2022" @default.
- W4304587443 type Work @default.
- W4304587443 citedByCount "4" @default.
- W4304587443 countsByYear W43045874432023 @default.
- W4304587443 crossrefType "journal-article" @default.
- W4304587443 hasAuthorship W4304587443A5013164931 @default.
- W4304587443 hasAuthorship W4304587443A5041199457 @default.
- W4304587443 hasAuthorship W4304587443A5080967998 @default.
- W4304587443 hasAuthorship W4304587443A5083885492 @default.
- W4304587443 hasBestOaLocation W43045874432 @default.
- W4304587443 hasConcept C11413529 @default.
- W4304587443 hasConcept C119857082 @default.
- W4304587443 hasConcept C121332964 @default.
- W4304587443 hasConcept C154945302 @default.
- W4304587443 hasConcept C192562407 @default.
- W4304587443 hasConcept C20788544 @default.
- W4304587443 hasConcept C2778755073 @default.
- W4304587443 hasConcept C41008148 @default.
- W4304587443 hasConcept C459310 @default.
- W4304587443 hasConcept C49040817 @default.
- W4304587443 hasConcept C62520636 @default.
- W4304587443 hasConceptScore W4304587443C11413529 @default.
- W4304587443 hasConceptScore W4304587443C119857082 @default.
- W4304587443 hasConceptScore W4304587443C121332964 @default.
- W4304587443 hasConceptScore W4304587443C154945302 @default.
- W4304587443 hasConceptScore W4304587443C192562407 @default.
- W4304587443 hasConceptScore W4304587443C20788544 @default.
- W4304587443 hasConceptScore W4304587443C2778755073 @default.
- W4304587443 hasConceptScore W4304587443C41008148 @default.
- W4304587443 hasConceptScore W4304587443C459310 @default.
- W4304587443 hasConceptScore W4304587443C49040817 @default.
- W4304587443 hasConceptScore W4304587443C62520636 @default.
- W4304587443 hasFunder F4320328328 @default.
- W4304587443 hasFunder F4320331528 @default.
- W4304587443 hasIssue "12" @default.
- W4304587443 hasLocation W43045874431 @default.
- W4304587443 hasLocation W43045874432 @default.
- W4304587443 hasOpenAccess W4304587443 @default.
- W4304587443 hasPrimaryLocation W43045874431 @default.
- W4304587443 hasRelatedWork W2961085424 @default.
- W4304587443 hasRelatedWork W3046775127 @default.