FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3002289736> ?p ?o ?g. }

• W3002289736 endingPage "065005" @default.
• W3002289736 startingPage "065005" @default.
• W3002289736 abstract "Abstract Recovering a function or high-dimensional parameter vector from indirect measurements is a central task in various scientific areas. Several methods for solving such inverse problems are well developed and well understood. Recently, novel algorithms using deep learning and neural networks for inverse problems appeared. While still in their infancy, these techniques show astonishing performance for applications like low-dose CT or various sparse data problems. However, there are few theoretical results for deep learning in inverse problems. In this paper, we establish a complete convergence analysis for the proposed NETT (network Tikhonov) approach to inverse problems. NETT considers nearly data-consistent solutions having small value of a regularizer defined by a trained neural network. We derive well-posedness results and quantitative error estimates, and propose a possible strategy for training the regularizer. Our theoretical results and framework are different from any previous work using neural networks for solving inverse problems. A possible data driven regularizer is proposed. Numerical results are presented for a tomographic sparse data problem, which demonstrate good performance of NETT even for unknowns of different type from the training data. To derive the convergence and convergence rates results we introduce a new framework based on the absolute Bregman distance generalizing the standard Bregman distance from the convex to the non-convex case." @default.
• W3002289736 created "2020-01-30" @default.
• W3002289736 creator A5014875283 @default.
• W3002289736 creator A5024770025 @default.
• W3002289736 creator A5026767648 @default.
• W3002289736 creator A5054830960 @default.
• W3002289736 date "2020-06-01" @default.
• W3002289736 modified "2023-10-17" @default.
• W3002289736 title "NETT: solving inverse problems with deep neural networks" @default.
• W3002289736 cites W1978477307 @default.
• W3002289736 cites W1984868585 @default.
• W3002289736 cites W2023206259 @default.
• W3002289736 cites W2023299560 @default.
• W3002289736 cites W2060993709 @default.
• W3002289736 cites W2068926508 @default.
• W3002289736 cites W2069912449 @default.
• W3002289736 cites W2073898807 @default.
• W3002289736 cites W2076264645 @default.
• W3002289736 cites W2078006497 @default.
• W3002289736 cites W2082823585 @default.
• W3002289736 cites W2098914003 @default.
• W3002289736 cites W2115706991 @default.
• W3002289736 cites W2127114523 @default.
• W3002289736 cites W2133665775 @default.
• W3002289736 cites W2160547390 @default.
• W3002289736 cites W2321048932 @default.
• W3002289736 cites W2520016695 @default.
• W3002289736 cites W2570202822 @default.
• W3002289736 cites W2573726823 @default.
• W3002289736 cites W2574952845 @default.
• W3002289736 cites W2594014149 @default.
• W3002289736 cites W2604388535 @default.
• W3002289736 cites W2950042078 @default.
• W3002289736 cites W2962850795 @default.
• W3002289736 cites W3010771391 @default.
• W3002289736 cites W3100730608 @default.
• W3002289736 cites W3101765447 @default.
• W3002289736 cites W4252317729 @default.
• W3002289736 doi "https://doi.org/10.1088/1361-6420/ab6d57" @default.
• W3002289736 hasPublicationYear "2020" @default.
• W3002289736 type Work @default.
• W3002289736 sameAs 3002289736 @default.
• W3002289736 citedByCount "129" @default.
• W3002289736 countsByYear W30022897362018 @default.
• W3002289736 countsByYear W30022897362019 @default.
• W3002289736 countsByYear W30022897362020 @default.
• W3002289736 countsByYear W30022897362021 @default.
• W3002289736 countsByYear W30022897362022 @default.
• W3002289736 countsByYear W30022897362023 @default.
• W3002289736 crossrefType "journal-article" @default.
• W3002289736 hasAuthorship W3002289736A5014875283 @default.
• W3002289736 hasAuthorship W3002289736A5024770025 @default.
• W3002289736 hasAuthorship W3002289736A5026767648 @default.
• W3002289736 hasAuthorship W3002289736A5054830960 @default.
• W3002289736 hasBestOaLocation W30022897361 @default.
• W3002289736 hasConcept C112680207 @default.
• W3002289736 hasConcept C11413529 @default.
• W3002289736 hasConcept C126255220 @default.
• W3002289736 hasConcept C134306372 @default.
• W3002289736 hasConcept C135252773 @default.
• W3002289736 hasConcept C14036430 @default.
• W3002289736 hasConcept C145446738 @default.
• W3002289736 hasConcept C149073432 @default.
• W3002289736 hasConcept C152442038 @default.
• W3002289736 hasConcept C154945302 @default.
• W3002289736 hasConcept C162324750 @default.
• W3002289736 hasConcept C207467116 @default.
• W3002289736 hasConcept C2524010 @default.
• W3002289736 hasConcept C2777303404 @default.
• W3002289736 hasConcept C28826006 @default.
• W3002289736 hasConcept C33923547 @default.
• W3002289736 hasConcept C41008148 @default.
• W3002289736 hasConcept C50522688 @default.
• W3002289736 hasConcept C50644808 @default.
• W3002289736 hasConcept C78458016 @default.
• W3002289736 hasConcept C86803240 @default.
• W3002289736 hasConceptScore W3002289736C112680207 @default.
• W3002289736 hasConceptScore W3002289736C11413529 @default.
• W3002289736 hasConceptScore W3002289736C126255220 @default.
• W3002289736 hasConceptScore W3002289736C134306372 @default.
• W3002289736 hasConceptScore W3002289736C135252773 @default.
• W3002289736 hasConceptScore W3002289736C14036430 @default.
• W3002289736 hasConceptScore W3002289736C145446738 @default.
• W3002289736 hasConceptScore W3002289736C149073432 @default.
• W3002289736 hasConceptScore W3002289736C152442038 @default.
• W3002289736 hasConceptScore W3002289736C154945302 @default.
• W3002289736 hasConceptScore W3002289736C162324750 @default.
• W3002289736 hasConceptScore W3002289736C207467116 @default.
• W3002289736 hasConceptScore W3002289736C2524010 @default.
• W3002289736 hasConceptScore W3002289736C2777303404 @default.
• W3002289736 hasConceptScore W3002289736C28826006 @default.
• W3002289736 hasConceptScore W3002289736C33923547 @default.
• W3002289736 hasConceptScore W3002289736C41008148 @default.
• W3002289736 hasConceptScore W3002289736C50522688 @default.
• W3002289736 hasConceptScore W3002289736C50644808 @default.
• W3002289736 hasConceptScore W3002289736C78458016 @default.
• W3002289736 hasConceptScore W3002289736C86803240 @default.
• W3002289736 hasFunder F4320320879 @default.

• next