Matches in SemOpenAlex for { <https://semopenalex.org/work/W3089336059> ?p ?o ?g. }
- W3089336059 abstract "We consider the task of solving generic inverse problems, where one wishes to determine the hidden parameters of a natural system that will give rise to a particular set of measurements. Recently many new approaches based upon deep learning have arisen generating impressive results. We conceptualize these models as different schemes for efficiently, but randomly, exploring the space of possible inverse solutions. As a result, the accuracy of each approach should be evaluated as a function of time rather than a single estimated solution, as is often done now. Using this metric, we compare several state-of-the-art inverse modeling approaches on four benchmark tasks: two existing tasks, one simple task for visualization and one new task from metamaterial design. Finally, inspired by our conception of the inverse problem, we explore a solution that uses a deep learning model to approximate the forward model, and then uses backpropagation to search for good inverse solutions. This approach, termed the neural-adjoint, achieves the best performance in many scenarios." @default.
- W3089336059 created "2020-10-01" @default.
- W3089336059 creator A5007239332 @default.
- W3089336059 creator A5026584916 @default.
- W3089336059 creator A5048895233 @default.
- W3089336059 date "2020-09-27" @default.
- W3089336059 modified "2023-09-26" @default.
- W3089336059 title "Benchmarking deep inverse models over time, and the neural-adjoint method" @default.
- W3089336059 cites W1522301498 @default.
- W3089336059 cites W1579853615 @default.
- W3089336059 cites W1583912456 @default.
- W3089336059 cites W1866230956 @default.
- W3089336059 cites W2043968544 @default.
- W3089336059 cites W2069697210 @default.
- W3089336059 cites W2070792261 @default.
- W3089336059 cites W2131241448 @default.
- W3089336059 cites W2212660284 @default.
- W3089336059 cites W2409550820 @default.
- W3089336059 cites W2766162919 @default.
- W3089336059 cites W2775280502 @default.
- W3089336059 cites W2785389871 @default.
- W3089336059 cites W2803281408 @default.
- W3089336059 cites W2887540873 @default.
- W3089336059 cites W2891198385 @default.
- W3089336059 cites W2911422441 @default.
- W3089336059 cites W2914973752 @default.
- W3089336059 cites W2951004968 @default.
- W3089336059 cites W2962721615 @default.
- W3089336059 cites W2962793481 @default.
- W3089336059 cites W2963613996 @default.
- W3089336059 cites W2968528838 @default.
- W3089336059 cites W3101600778 @default.
- W3089336059 cites W3125097811 @default.
- W3089336059 cites W627530429 @default.
- W3089336059 hasPublicationYear "2020" @default.
- W3089336059 type Work @default.
- W3089336059 sameAs 3089336059 @default.
- W3089336059 citedByCount "1" @default.
- W3089336059 countsByYear W30893360592022 @default.
- W3089336059 crossrefType "posted-content" @default.
- W3089336059 hasAuthorship W3089336059A5007239332 @default.
- W3089336059 hasAuthorship W3089336059A5026584916 @default.
- W3089336059 hasAuthorship W3089336059A5048895233 @default.
- W3089336059 hasConcept C108583219 @default.
- W3089336059 hasConcept C111472728 @default.
- W3089336059 hasConcept C11413529 @default.
- W3089336059 hasConcept C119857082 @default.
- W3089336059 hasConcept C13280743 @default.
- W3089336059 hasConcept C134306372 @default.
- W3089336059 hasConcept C135252773 @default.
- W3089336059 hasConcept C138885662 @default.
- W3089336059 hasConcept C14036430 @default.
- W3089336059 hasConcept C144133560 @default.
- W3089336059 hasConcept C154945302 @default.
- W3089336059 hasConcept C155032097 @default.
- W3089336059 hasConcept C162324750 @default.
- W3089336059 hasConcept C162853370 @default.
- W3089336059 hasConcept C176217482 @default.
- W3089336059 hasConcept C177264268 @default.
- W3089336059 hasConcept C185798385 @default.
- W3089336059 hasConcept C187736073 @default.
- W3089336059 hasConcept C199360897 @default.
- W3089336059 hasConcept C205649164 @default.
- W3089336059 hasConcept C207467116 @default.
- W3089336059 hasConcept C21547014 @default.
- W3089336059 hasConcept C2524010 @default.
- W3089336059 hasConcept C2780451532 @default.
- W3089336059 hasConcept C2780586882 @default.
- W3089336059 hasConcept C33923547 @default.
- W3089336059 hasConcept C41008148 @default.
- W3089336059 hasConcept C50644808 @default.
- W3089336059 hasConcept C78458016 @default.
- W3089336059 hasConcept C86251818 @default.
- W3089336059 hasConcept C86803240 @default.
- W3089336059 hasConceptScore W3089336059C108583219 @default.
- W3089336059 hasConceptScore W3089336059C111472728 @default.
- W3089336059 hasConceptScore W3089336059C11413529 @default.
- W3089336059 hasConceptScore W3089336059C119857082 @default.
- W3089336059 hasConceptScore W3089336059C13280743 @default.
- W3089336059 hasConceptScore W3089336059C134306372 @default.
- W3089336059 hasConceptScore W3089336059C135252773 @default.
- W3089336059 hasConceptScore W3089336059C138885662 @default.
- W3089336059 hasConceptScore W3089336059C14036430 @default.
- W3089336059 hasConceptScore W3089336059C144133560 @default.
- W3089336059 hasConceptScore W3089336059C154945302 @default.
- W3089336059 hasConceptScore W3089336059C155032097 @default.
- W3089336059 hasConceptScore W3089336059C162324750 @default.
- W3089336059 hasConceptScore W3089336059C162853370 @default.
- W3089336059 hasConceptScore W3089336059C176217482 @default.
- W3089336059 hasConceptScore W3089336059C177264268 @default.
- W3089336059 hasConceptScore W3089336059C185798385 @default.
- W3089336059 hasConceptScore W3089336059C187736073 @default.
- W3089336059 hasConceptScore W3089336059C199360897 @default.
- W3089336059 hasConceptScore W3089336059C205649164 @default.
- W3089336059 hasConceptScore W3089336059C207467116 @default.
- W3089336059 hasConceptScore W3089336059C21547014 @default.
- W3089336059 hasConceptScore W3089336059C2524010 @default.
- W3089336059 hasConceptScore W3089336059C2780451532 @default.
- W3089336059 hasConceptScore W3089336059C2780586882 @default.
- W3089336059 hasConceptScore W3089336059C33923547 @default.