FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2971387483> ?p ?o ?g. }

• W2971387483 abstract "Neural networks are discrete entities: subdivided into discrete layers and parametrized by weights which are iteratively optimized via difference equations. Recent work proposes networks with layer outputs which are no longer quantized but are solutions of an ordinary differential equation (ODE); however, these networks are still optimized via discrete methods (e.g. gradient descent). In this paper, we explore a different direction: namely, we propose a novel framework for learning in which the parameters themselves are solutions of ODEs. By viewing the optimization process as the evolution of a port-Hamiltonian system, we can ensure convergence to a minimum of the objective function. Numerical experiments have been performed to show the validity and effectiveness of the proposed methods." @default.
• W2971387483 created "2019-09-12" @default.
• W2971387483 creator A5021260328 @default.
• W2971387483 creator A5023509025 @default.
• W2971387483 creator A5034743350 @default.
• W2971387483 creator A5053046176 @default.
• W2971387483 creator A5064103302 @default.
• W2971387483 creator A5075056195 @default.
• W2971387483 creator A5078213488 @default.
• W2971387483 date "2019-09-05" @default.
• W2971387483 modified "2023-09-30" @default.
• W2971387483 title "Port-Hamiltonian Approach to Neural Network Training" @default.
• W2971387483 cites W1526120274 @default.
• W2971387483 cites W1553823556 @default.
• W2971387483 cites W1559036903 @default.
• W2971387483 cites W1573485417 @default.
• W2971387483 cites W2005490094 @default.
• W2971387483 cites W2042492924 @default.
• W2971387483 cites W2048253740 @default.
• W2971387483 cites W2096876511 @default.
• W2971387483 cites W2108810732 @default.
• W2971387483 cites W2128084896 @default.
• W2971387483 cites W2128865943 @default.
• W2971387483 cites W2139361041 @default.
• W2971387483 cites W2144513243 @default.
• W2971387483 cites W2148101780 @default.
• W2971387483 cites W2194775991 @default.
• W2971387483 cites W2766736793 @default.
• W2971387483 cites W2893749619 @default.
• W2971387483 cites W2962742960 @default.
• W2971387483 cites W2962933129 @default.
• W2971387483 cites W2963097630 @default.
• W2971387483 cites W2963150697 @default.
• W2971387483 cites W2963341956 @default.
• W2971387483 cites W2963480765 @default.
• W2971387483 cites W2963755523 @default.
• W2971387483 cites W2964121744 @default.
• W2971387483 cites W2968917279 @default.
• W2971387483 cites W2974916071 @default.
• W2971387483 cites W3146803896 @default.
• W2971387483 cites W608564660 @default.
• W2971387483 doi "https://doi.org/10.48550/arxiv.1909.02702" @default.
• W2971387483 hasPublicationYear "2019" @default.
• W2971387483 type Work @default.
• W2971387483 sameAs 2971387483 @default.
• W2971387483 citedByCount "3" @default.
• W2971387483 countsByYear W29713874832020 @default.
• W2971387483 countsByYear W29713874832021 @default.
• W2971387483 crossrefType "posted-content" @default.
• W2971387483 hasAuthorship W2971387483A5021260328 @default.
• W2971387483 hasAuthorship W2971387483A5023509025 @default.
• W2971387483 hasAuthorship W2971387483A5034743350 @default.
• W2971387483 hasAuthorship W2971387483A5053046176 @default.
• W2971387483 hasAuthorship W2971387483A5064103302 @default.
• W2971387483 hasAuthorship W2971387483A5075056195 @default.
• W2971387483 hasAuthorship W2971387483A5078213488 @default.
• W2971387483 hasBestOaLocation W29713874831 @default.
• W2971387483 hasConcept C119599485 @default.
• W2971387483 hasConcept C126255220 @default.
• W2971387483 hasConcept C127413603 @default.
• W2971387483 hasConcept C130787639 @default.
• W2971387483 hasConcept C134306372 @default.
• W2971387483 hasConcept C153258448 @default.
• W2971387483 hasConcept C154945302 @default.
• W2971387483 hasConcept C162324750 @default.
• W2971387483 hasConcept C2777303404 @default.
• W2971387483 hasConcept C28826006 @default.
• W2971387483 hasConcept C32802771 @default.
• W2971387483 hasConcept C33923547 @default.
• W2971387483 hasConcept C34862557 @default.
• W2971387483 hasConcept C41008148 @default.
• W2971387483 hasConcept C50522688 @default.
• W2971387483 hasConcept C50644808 @default.
• W2971387483 hasConcept C51544822 @default.
• W2971387483 hasConcept C78045399 @default.
• W2971387483 hasConceptScore W2971387483C119599485 @default.
• W2971387483 hasConceptScore W2971387483C126255220 @default.
• W2971387483 hasConceptScore W2971387483C127413603 @default.
• W2971387483 hasConceptScore W2971387483C130787639 @default.
• W2971387483 hasConceptScore W2971387483C134306372 @default.
• W2971387483 hasConceptScore W2971387483C153258448 @default.
• W2971387483 hasConceptScore W2971387483C154945302 @default.
• W2971387483 hasConceptScore W2971387483C162324750 @default.
• W2971387483 hasConceptScore W2971387483C2777303404 @default.
• W2971387483 hasConceptScore W2971387483C28826006 @default.
• W2971387483 hasConceptScore W2971387483C32802771 @default.
• W2971387483 hasConceptScore W2971387483C33923547 @default.
• W2971387483 hasConceptScore W2971387483C34862557 @default.
• W2971387483 hasConceptScore W2971387483C41008148 @default.
• W2971387483 hasConceptScore W2971387483C50522688 @default.
• W2971387483 hasConceptScore W2971387483C50644808 @default.
• W2971387483 hasConceptScore W2971387483C51544822 @default.
• W2971387483 hasConceptScore W2971387483C78045399 @default.
• W2971387483 hasLocation W29713874831 @default.
• W2971387483 hasLocation W29713874832 @default.
• W2971387483 hasOpenAccess W2971387483 @default.
• W2971387483 hasPrimaryLocation W29713874831 @default.
• W2971387483 hasRelatedWork W1750424384 @default.
• W2971387483 hasRelatedWork W2048795484 @default.
• W2971387483 hasRelatedWork W2263887205 @default.

• next