Matches in SemOpenAlex for { <https://semopenalex.org/work/W3040090787> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W3040090787 endingPage "209" @default.
- W3040090787 startingPage "203" @default.
- W3040090787 abstract "In many practical situations, there exist several representations, each of which is convenient for some operations, and many data processing algorithms involve transforming back and forth between these representations. Many such transformations are computationally time-consuming when performed exactly. So, taking into account that input data is usually only 1–10% accurate anyway, it makes sense to replace time-consuming exact transformations with faster approximate ones. One of the natural ways to get a fast-computing approximation to a transformation is to train the corresponding neural network. The problem is that if we train A-to-B and B-to-A networks separately, the resulting approximate transformations are only approximately inverse to each other. As a result, each time we transform back and forth, we add new approximation error—and the accumulated error may become significant. In this paper, we show how we can avoid this accumulation. Specifically, we show how to train A-to-B and B-to-A neural networks so that the resulting transformations are (almost) exact inverses." @default.
- W3040090787 created "2020-07-10" @default.
- W3040090787 creator A5016827109 @default.
- W3040090787 creator A5038154358 @default.
- W3040090787 creator A5040035817 @default.
- W3040090787 creator A5049362452 @default.
- W3040090787 date "2022-01-01" @default.
- W3040090787 modified "2023-09-23" @default.
- W3040090787 title "How to Train A-to-B and B-to-A Neural Networks So That the Resulting Transformations Are (Almost) Exact Inverses" @default.
- W3040090787 cites W2962949867 @default.
- W3040090787 doi "https://doi.org/10.1007/978-3-030-97273-8_14" @default.
- W3040090787 hasPublicationYear "2022" @default.
- W3040090787 type Work @default.
- W3040090787 sameAs 3040090787 @default.
- W3040090787 citedByCount "0" @default.
- W3040090787 crossrefType "book-chapter" @default.
- W3040090787 hasAuthorship W3040090787A5016827109 @default.
- W3040090787 hasAuthorship W3040090787A5038154358 @default.
- W3040090787 hasAuthorship W3040090787A5040035817 @default.
- W3040090787 hasAuthorship W3040090787A5049362452 @default.
- W3040090787 hasBestOaLocation W30400907872 @default.
- W3040090787 hasConcept C104317684 @default.
- W3040090787 hasConcept C11413529 @default.
- W3040090787 hasConcept C122383733 @default.
- W3040090787 hasConcept C154945302 @default.
- W3040090787 hasConcept C185592680 @default.
- W3040090787 hasConcept C204241405 @default.
- W3040090787 hasConcept C207467116 @default.
- W3040090787 hasConcept C2524010 @default.
- W3040090787 hasConcept C33923547 @default.
- W3040090787 hasConcept C41008148 @default.
- W3040090787 hasConcept C50644808 @default.
- W3040090787 hasConcept C55493867 @default.
- W3040090787 hasConcept C80444323 @default.
- W3040090787 hasConceptScore W3040090787C104317684 @default.
- W3040090787 hasConceptScore W3040090787C11413529 @default.
- W3040090787 hasConceptScore W3040090787C122383733 @default.
- W3040090787 hasConceptScore W3040090787C154945302 @default.
- W3040090787 hasConceptScore W3040090787C185592680 @default.
- W3040090787 hasConceptScore W3040090787C204241405 @default.
- W3040090787 hasConceptScore W3040090787C207467116 @default.
- W3040090787 hasConceptScore W3040090787C2524010 @default.
- W3040090787 hasConceptScore W3040090787C33923547 @default.
- W3040090787 hasConceptScore W3040090787C41008148 @default.
- W3040090787 hasConceptScore W3040090787C50644808 @default.
- W3040090787 hasConceptScore W3040090787C55493867 @default.
- W3040090787 hasConceptScore W3040090787C80444323 @default.
- W3040090787 hasLocation W30400907871 @default.
- W3040090787 hasLocation W30400907872 @default.
- W3040090787 hasOpenAccess W3040090787 @default.
- W3040090787 hasPrimaryLocation W30400907871 @default.
- W3040090787 hasRelatedWork W2335520227 @default.
- W3040090787 hasRelatedWork W2351491280 @default.
- W3040090787 hasRelatedWork W2365767001 @default.
- W3040090787 hasRelatedWork W2369456215 @default.
- W3040090787 hasRelatedWork W2379147087 @default.
- W3040090787 hasRelatedWork W2386387936 @default.
- W3040090787 hasRelatedWork W2392110728 @default.
- W3040090787 hasRelatedWork W2969549175 @default.
- W3040090787 hasRelatedWork W2990303645 @default.
- W3040090787 hasRelatedWork W303980170 @default.
- W3040090787 isParatext "false" @default.
- W3040090787 isRetracted "false" @default.
- W3040090787 magId "3040090787" @default.
- W3040090787 workType "book-chapter" @default.