FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3088017310> ?p ?o ?g. }

• W3088017310 endingPage "1414" @default.
• W3088017310 startingPage "1403" @default.
• W3088017310 abstract "Critical aspects of computational imaging systems, such as experimental design and image priors, can be optimized through deep networks formed by the unrolled iterations of classical physics-based reconstructions. Termed physics-based networks, they incorporate both the known physics of the system via its forward model, and the power of deep learning via data-driven training. However, for realistic large-scale physics-based networks, computing gradients via backpropagation is infeasible due to the memory limitations of graphics processing units. In this work, we propose a memory-efficient learning procedure that exploits the reversibility of the network's layers to enable physics-based learning for large-scale computational imaging systems. We demonstrate our method on a compressed sensing example, as well as two large-scale real-world systems: 3D multi-channel magnetic resonance imaging and super-resolution optical microscopy." @default.
• W3088017310 created "2020-10-01" @default.
• W3088017310 creator A5009837937 @default.
• W3088017310 creator A5013394127 @default.
• W3088017310 creator A5014838961 @default.
• W3088017310 creator A5024309830 @default.
• W3088017310 creator A5056163027 @default.
• W3088017310 creator A5082297273 @default.
• W3088017310 creator A5091835589 @default.
• W3088017310 date "2020-01-01" @default.
• W3088017310 modified "2023-10-16" @default.
• W3088017310 title "Memory-Efficient Learning for Large-Scale Computational Imaging" @default.
• W3088017310 cites W1458771408 @default.
• W3088017310 cites W1906770428 @default.
• W3088017310 cites W1996726072 @default.
• W3088017310 cites W2047602908 @default.
• W3088017310 cites W2053270078 @default.
• W3088017310 cites W2100556411 @default.
• W3088017310 cites W2101675075 @default.
• W3088017310 cites W2122548617 @default.
• W3088017310 cites W2146481498 @default.
• W3088017310 cites W2194775991 @default.
• W3088017310 cites W2478429860 @default.
• W3088017310 cites W2604388535 @default.
• W3088017310 cites W2613155248 @default.
• W3088017310 cites W2675611360 @default.
• W3088017310 cites W2798559986 @default.
• W3088017310 cites W2809900749 @default.
• W3088017310 cites W2885076424 @default.
• W3088017310 cites W2930326357 @default.
• W3088017310 cites W2972741102 @default.
• W3088017310 cites W3015567121 @default.
• W3088017310 cites W3021094251 @default.
• W3088017310 cites W3098933358 @default.
• W3088017310 cites W3100730608 @default.
• W3088017310 cites W4244393449 @default.
• W3088017310 cites W4249760698 @default.
• W3088017310 cites W4250955649 @default.
• W3088017310 cites W4292692451 @default.
• W3088017310 doi "https://doi.org/10.1109/tci.2020.3025735" @default.
• W3088017310 hasPublicationYear "2020" @default.
• W3088017310 type Work @default.
• W3088017310 sameAs 3088017310 @default.
• W3088017310 citedByCount "37" @default.
• W3088017310 countsByYear W30880173102020 @default.
• W3088017310 countsByYear W30880173102021 @default.
• W3088017310 countsByYear W30880173102022 @default.
• W3088017310 countsByYear W30880173102023 @default.
• W3088017310 crossrefType "journal-article" @default.
• W3088017310 hasAuthorship W3088017310A5009837937 @default.
• W3088017310 hasAuthorship W3088017310A5013394127 @default.
• W3088017310 hasAuthorship W3088017310A5014838961 @default.
• W3088017310 hasAuthorship W3088017310A5024309830 @default.
• W3088017310 hasAuthorship W3088017310A5056163027 @default.
• W3088017310 hasAuthorship W3088017310A5082297273 @default.
• W3088017310 hasAuthorship W3088017310A5091835589 @default.
• W3088017310 hasBestOaLocation W30880173101 @default.
• W3088017310 hasConcept C108583219 @default.
• W3088017310 hasConcept C121332964 @default.
• W3088017310 hasConcept C121684516 @default.
• W3088017310 hasConcept C124851039 @default.
• W3088017310 hasConcept C154945302 @default.
• W3088017310 hasConcept C173608175 @default.
• W3088017310 hasConcept C21442007 @default.
• W3088017310 hasConcept C2778755073 @default.
• W3088017310 hasConcept C2779851693 @default.
• W3088017310 hasConcept C41008148 @default.
• W3088017310 hasConcept C459310 @default.
• W3088017310 hasConcept C50644808 @default.
• W3088017310 hasConcept C62520636 @default.
• W3088017310 hasConceptScore W3088017310C108583219 @default.
• W3088017310 hasConceptScore W3088017310C121332964 @default.
• W3088017310 hasConceptScore W3088017310C121684516 @default.
• W3088017310 hasConceptScore W3088017310C124851039 @default.
• W3088017310 hasConceptScore W3088017310C154945302 @default.
• W3088017310 hasConceptScore W3088017310C173608175 @default.
• W3088017310 hasConceptScore W3088017310C21442007 @default.
• W3088017310 hasConceptScore W3088017310C2778755073 @default.
• W3088017310 hasConceptScore W3088017310C2779851693 @default.
• W3088017310 hasConceptScore W3088017310C41008148 @default.
• W3088017310 hasConceptScore W3088017310C459310 @default.
• W3088017310 hasConceptScore W3088017310C50644808 @default.
• W3088017310 hasConceptScore W3088017310C62520636 @default.
• W3088017310 hasFunder F4320306202 @default.
• W3088017310 hasFunder F4320320924 @default.
• W3088017310 hasFunder F4320332161 @default.
• W3088017310 hasFunder F4320335353 @default.
• W3088017310 hasLocation W30880173101 @default.
• W3088017310 hasLocation W30880173102 @default.
• W3088017310 hasOpenAccess W3088017310 @default.
• W3088017310 hasPrimaryLocation W30880173101 @default.
• W3088017310 hasRelatedWork W1936382095 @default.
• W3088017310 hasRelatedWork W1990331039 @default.
• W3088017310 hasRelatedWork W2056246470 @default.
• W3088017310 hasRelatedWork W2095734710 @default.
• W3088017310 hasRelatedWork W2312553612 @default.
• W3088017310 hasRelatedWork W2319181367 @default.
• W3088017310 hasRelatedWork W2322151118 @default.

• next