Matches in SemOpenAlex for { <https://semopenalex.org/work/W3091118633> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3091118633 abstract "Quantum machine learning has the potential for broad industrial applications, and the development of quantum algorithms for improving the performance of neural networks is of particular interest given the central role they play in machine learning today. In this paper we present quantum algorithms for training and evaluating feedforward neural networks based on the canonical classical feedforward and backpropagation algorithms. Our algorithms rely on an efficient quantum subroutine for approximating the inner products between vectors in a robust way, and on implicitly storing large intermediate values in quantum random access memory for fast retrieval at later stages. The running times of our algorithms can be quadratically faster in the size of the network than their standard classical counterparts since they depend linearly on the number of neurons in the network, as opposed to the number of connections between neurons as in the classical case. This makes our algorithms suited for large-scale, highly-connected networks where the number of edges in the network dominates the classical algorithmic running time. Furthermore, networks trained by our quantum algorithm may have an intrinsic resilience to overfitting, as the algorithm naturally mimics the effects of classical techniques such as drop-out used to regularize networks. Our algorithms can also be used as the basis for new quantum-inspired classical algorithms which have the same dependence on the network dimensions as their quantum counterparts, but with quadratic overhead in other parameters that makes them relatively impractical." @default.
- W3091118633 created "2020-10-08" @default.
- W3091118633 creator A5002447654 @default.
- W3091118633 creator A5008663435 @default.
- W3091118633 creator A5024725897 @default.
- W3091118633 creator A5077333536 @default.
- W3091118633 date "2019-12-15" @default.
- W3091118633 modified "2023-10-17" @default.
- W3091118633 title "Quantum algorithms for feedforward neural networks" @default.
- W3091118633 cites W1498436455 @default.
- W3091118633 cites W1990514347 @default.
- W3091118633 cites W2051446825 @default.
- W3091118633 cites W2094908058 @default.
- W3091118633 cites W2103956991 @default.
- W3091118633 cites W2121981260 @default.
- W3091118633 cites W2179731956 @default.
- W3091118633 cites W2194775991 @default.
- W3091118633 cites W2489886790 @default.
- W3091118633 cites W2560386163 @default.
- W3091118633 cites W2579928628 @default.
- W3091118633 cites W2607911764 @default.
- W3091118633 cites W2607956695 @default.
- W3091118633 cites W2736592352 @default.
- W3091118633 cites W2754084392 @default.
- W3091118633 cites W2786167326 @default.
- W3091118633 cites W2792315573 @default.
- W3091118633 cites W2792946961 @default.
- W3091118633 cites W2896712926 @default.
- W3091118633 cites W2923917339 @default.
- W3091118633 cites W3101135395 @default.
- W3091118633 cites W3104450852 @default.
- W3091118633 cites W3104599990 @default.
- W3091118633 cites W3105870134 @default.
- W3091118633 cites W3106243186 @default.
- W3091118633 hasPublicationYear "2019" @default.
- W3091118633 type Work @default.
- W3091118633 sameAs 3091118633 @default.
- W3091118633 citedByCount "11" @default.
- W3091118633 countsByYear W30911186332019 @default.
- W3091118633 countsByYear W30911186332020 @default.
- W3091118633 countsByYear W30911186332021 @default.
- W3091118633 crossrefType "posted-content" @default.
- W3091118633 hasAuthorship W3091118633A5002447654 @default.
- W3091118633 hasAuthorship W3091118633A5008663435 @default.
- W3091118633 hasAuthorship W3091118633A5024725897 @default.
- W3091118633 hasAuthorship W3091118633A5077333536 @default.
- W3091118633 hasBestOaLocation W30911186332 @default.
- W3091118633 hasConcept C11413529 @default.
- W3091118633 hasConcept C121332964 @default.
- W3091118633 hasConcept C137019171 @default.
- W3091118633 hasConcept C154945302 @default.
- W3091118633 hasConcept C186468114 @default.
- W3091118633 hasConcept C195956108 @default.
- W3091118633 hasConcept C22019652 @default.
- W3091118633 hasConcept C2779094486 @default.
- W3091118633 hasConcept C41008148 @default.
- W3091118633 hasConcept C47702885 @default.
- W3091118633 hasConcept C50644808 @default.
- W3091118633 hasConcept C58053490 @default.
- W3091118633 hasConcept C62520636 @default.
- W3091118633 hasConcept C62641251 @default.
- W3091118633 hasConcept C84114770 @default.
- W3091118633 hasConceptScore W3091118633C11413529 @default.
- W3091118633 hasConceptScore W3091118633C121332964 @default.
- W3091118633 hasConceptScore W3091118633C137019171 @default.
- W3091118633 hasConceptScore W3091118633C154945302 @default.
- W3091118633 hasConceptScore W3091118633C186468114 @default.
- W3091118633 hasConceptScore W3091118633C195956108 @default.
- W3091118633 hasConceptScore W3091118633C22019652 @default.
- W3091118633 hasConceptScore W3091118633C2779094486 @default.
- W3091118633 hasConceptScore W3091118633C41008148 @default.
- W3091118633 hasConceptScore W3091118633C47702885 @default.
- W3091118633 hasConceptScore W3091118633C50644808 @default.
- W3091118633 hasConceptScore W3091118633C58053490 @default.
- W3091118633 hasConceptScore W3091118633C62520636 @default.
- W3091118633 hasConceptScore W3091118633C62641251 @default.
- W3091118633 hasConceptScore W3091118633C84114770 @default.
- W3091118633 hasLocation W30911186331 @default.
- W3091118633 hasLocation W30911186332 @default.
- W3091118633 hasOpenAccess W3091118633 @default.
- W3091118633 hasPrimaryLocation W30911186331 @default.
- W3091118633 hasRelatedWork W3163277323 @default.
- W3091118633 hasRelatedWork W3182433019 @default.
- W3091118633 hasRelatedWork W3184624667 @default.
- W3091118633 hasRelatedWork W3198146246 @default.
- W3091118633 hasRelatedWork W4206249451 @default.
- W3091118633 hasRelatedWork W4285326889 @default.
- W3091118633 hasRelatedWork W4289534122 @default.
- W3091118633 hasRelatedWork W4298182858 @default.
- W3091118633 hasRelatedWork W4313680096 @default.
- W3091118633 hasRelatedWork W4378222347 @default.
- W3091118633 isParatext "false" @default.
- W3091118633 isRetracted "false" @default.
- W3091118633 magId "3091118633" @default.
- W3091118633 workType "article" @default.