Matches in SemOpenAlex for { <https://semopenalex.org/work/W4300852227> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4300852227 abstract "Tensor networks have found a wide use in a variety of applications in physics and computer science, recently leading to both theoretical insights as well as practical algorithms in machine learning. In this work we explore the connection between tensor networks and probabilistic graphical models, and show that it motivates the definition of generalized tensor networks where information from a tensor can be copied and reused in other parts of the network. We discuss the relationship between generalized tensor network architectures used in quantum physics, such as string-bond states, and architectures commonly used in machine learning. We provide an algorithm to train these networks in a supervised-learning context and show that they overcome the limitations of regular tensor networks in higher dimensions, while keeping the computation efficient. A method to combine neural networks and tensor networks as part of a common deep learning architecture is also introduced. We benchmark our algorithm for several generalized tensor network architectures on the task of classifying images and sounds, and show that they outperform previously introduced tensor-network algorithms. The models we consider also have a natural implementation on a quantum computer and may guide the development of near-term quantum machine learning architectures." @default.
- W4300852227 created "2022-10-04" @default.
- W4300852227 creator A5071162185 @default.
- W4300852227 creator A5077715469 @default.
- W4300852227 creator A5089434753 @default.
- W4300852227 date "2018-06-15" @default.
- W4300852227 modified "2023-10-14" @default.
- W4300852227 title "From probabilistic graphical models to generalized tensor networks for supervised learning" @default.
- W4300852227 doi "https://doi.org/10.48550/arxiv.1806.05964" @default.
- W4300852227 hasPublicationYear "2018" @default.
- W4300852227 type Work @default.
- W4300852227 citedByCount "1" @default.
- W4300852227 countsByYear W43008522272022 @default.
- W4300852227 crossrefType "posted-content" @default.
- W4300852227 hasAuthorship W4300852227A5071162185 @default.
- W4300852227 hasAuthorship W4300852227A5077715469 @default.
- W4300852227 hasAuthorship W4300852227A5089434753 @default.
- W4300852227 hasBestOaLocation W43008522271 @default.
- W4300852227 hasConcept C119857082 @default.
- W4300852227 hasConcept C13280743 @default.
- W4300852227 hasConcept C151730666 @default.
- W4300852227 hasConcept C154945302 @default.
- W4300852227 hasConcept C155281189 @default.
- W4300852227 hasConcept C155846161 @default.
- W4300852227 hasConcept C185798385 @default.
- W4300852227 hasConcept C202444582 @default.
- W4300852227 hasConcept C205649164 @default.
- W4300852227 hasConcept C2779343474 @default.
- W4300852227 hasConcept C33923547 @default.
- W4300852227 hasConcept C41008148 @default.
- W4300852227 hasConcept C49937458 @default.
- W4300852227 hasConcept C80444323 @default.
- W4300852227 hasConcept C86803240 @default.
- W4300852227 hasConceptScore W4300852227C119857082 @default.
- W4300852227 hasConceptScore W4300852227C13280743 @default.
- W4300852227 hasConceptScore W4300852227C151730666 @default.
- W4300852227 hasConceptScore W4300852227C154945302 @default.
- W4300852227 hasConceptScore W4300852227C155281189 @default.
- W4300852227 hasConceptScore W4300852227C155846161 @default.
- W4300852227 hasConceptScore W4300852227C185798385 @default.
- W4300852227 hasConceptScore W4300852227C202444582 @default.
- W4300852227 hasConceptScore W4300852227C205649164 @default.
- W4300852227 hasConceptScore W4300852227C2779343474 @default.
- W4300852227 hasConceptScore W4300852227C33923547 @default.
- W4300852227 hasConceptScore W4300852227C41008148 @default.
- W4300852227 hasConceptScore W4300852227C49937458 @default.
- W4300852227 hasConceptScore W4300852227C80444323 @default.
- W4300852227 hasConceptScore W4300852227C86803240 @default.
- W4300852227 hasLocation W43008522271 @default.
- W4300852227 hasLocation W43008522272 @default.
- W4300852227 hasOpenAccess W4300852227 @default.
- W4300852227 hasPrimaryLocation W43008522271 @default.
- W4300852227 hasRelatedWork W1601455886 @default.
- W4300852227 hasRelatedWork W2170784679 @default.
- W4300852227 hasRelatedWork W2958788635 @default.
- W4300852227 hasRelatedWork W2963058055 @default.
- W4300852227 hasRelatedWork W2994947658 @default.
- W4300852227 hasRelatedWork W3173872004 @default.
- W4300852227 hasRelatedWork W36077195 @default.
- W4300852227 hasRelatedWork W4221154940 @default.
- W4300852227 hasRelatedWork W4285600840 @default.
- W4300852227 hasRelatedWork W4288719182 @default.
- W4300852227 isParatext "false" @default.
- W4300852227 isRetracted "false" @default.
- W4300852227 workType "article" @default.