Matches in SemOpenAlex for { <https://semopenalex.org/work/W4295368766> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W4295368766 abstract "In this paper we study the concept of using the interaction between waves and a trainable medium in order to construct a matrix-vector multiplier. In particular we study such a device in the context of the backpropagation algorithm, which is commonly used for training neural networks. Here, the weights of the connections between neurons are trained by multiplying a `forward' signal with a backwards propagating `error' signal. We show that this concept can be extended to trainable media, where the gradient for the local wave number is given by multiplying signal waves and error waves. We provide a numerical example of such a system with waves traveling freely in a trainable medium, and we discuss a potential way to build such a device in an integrated photonics chip." @default.
- W4295368766 created "2022-09-13" @default.
- W4295368766 creator A5004032660 @default.
- W4295368766 creator A5007928811 @default.
- W4295368766 date "2015-09-30" @default.
- W4295368766 modified "2023-09-30" @default.
- W4295368766 title "Towards Trainable Media: Using Waves for Neural Network-Style Training" @default.
- W4295368766 doi "https://doi.org/10.48550/arxiv.1510.03776" @default.
- W4295368766 hasPublicationYear "2015" @default.
- W4295368766 type Work @default.
- W4295368766 citedByCount "0" @default.
- W4295368766 crossrefType "posted-content" @default.
- W4295368766 hasAuthorship W4295368766A5004032660 @default.
- W4295368766 hasAuthorship W4295368766A5007928811 @default.
- W4295368766 hasBestOaLocation W42953687661 @default.
- W4295368766 hasConcept C11413529 @default.
- W4295368766 hasConcept C151730666 @default.
- W4295368766 hasConcept C154945302 @default.
- W4295368766 hasConcept C155032097 @default.
- W4295368766 hasConcept C199360897 @default.
- W4295368766 hasConcept C2779343474 @default.
- W4295368766 hasConcept C2779843651 @default.
- W4295368766 hasConcept C2780801425 @default.
- W4295368766 hasConcept C41008148 @default.
- W4295368766 hasConcept C50644808 @default.
- W4295368766 hasConcept C86803240 @default.
- W4295368766 hasConceptScore W4295368766C11413529 @default.
- W4295368766 hasConceptScore W4295368766C151730666 @default.
- W4295368766 hasConceptScore W4295368766C154945302 @default.
- W4295368766 hasConceptScore W4295368766C155032097 @default.
- W4295368766 hasConceptScore W4295368766C199360897 @default.
- W4295368766 hasConceptScore W4295368766C2779343474 @default.
- W4295368766 hasConceptScore W4295368766C2779843651 @default.
- W4295368766 hasConceptScore W4295368766C2780801425 @default.
- W4295368766 hasConceptScore W4295368766C41008148 @default.
- W4295368766 hasConceptScore W4295368766C50644808 @default.
- W4295368766 hasConceptScore W4295368766C86803240 @default.
- W4295368766 hasLocation W42953687661 @default.
- W4295368766 hasOpenAccess W4295368766 @default.
- W4295368766 hasPrimaryLocation W42953687661 @default.
- W4295368766 hasRelatedWork W2105899231 @default.
- W4295368766 hasRelatedWork W2124052353 @default.
- W4295368766 hasRelatedWork W2124181104 @default.
- W4295368766 hasRelatedWork W2159443810 @default.
- W4295368766 hasRelatedWork W2348584318 @default.
- W4295368766 hasRelatedWork W2350832155 @default.
- W4295368766 hasRelatedWork W2362189222 @default.
- W4295368766 hasRelatedWork W2383491577 @default.
- W4295368766 hasRelatedWork W2391384657 @default.
- W4295368766 hasRelatedWork W2516580779 @default.
- W4295368766 isParatext "false" @default.
- W4295368766 isRetracted "false" @default.
- W4295368766 workType "article" @default.