Matches in SemOpenAlex for { <https://semopenalex.org/work/W3080147302> ?p ?o ?g. }
- W3080147302 abstract "S ummary Apart from discriminative models for classification and object detection tasks, the application of deep convolutional neural networks to basic research utilizing natural imaging data has been somewhat limited; particularly in cases where a set of interpretable features for downstream analysis is needed, a key requirement for many scientific investigations. We present an algorithm and training paradigm designed specifically to address this: decontextualized hierarchical representation learning (DHRL). By combining a generative model chaining procedure with a ladder network architecture and latent space regularization for inference, DHRL address the limitations of small datasets and encourages a disentangled set of hierarchically organized features. In addition to providing a tractable path for analyzing complex hierarchal patterns using variation inference, this approach is generative and can be directly combined with empirical and theoretical approaches. To highlight the extensibility and usefulness of DHRL, we demonstrate this method in application to a question from evolutionary biology." @default.
- W3080147302 created "2020-09-01" @default.
- W3080147302 creator A5031215616 @default.
- W3080147302 creator A5033076875 @default.
- W3080147302 creator A5034127832 @default.
- W3080147302 date "2020-08-25" @default.
- W3080147302 modified "2023-09-24" @default.
- W3080147302 title "Decontextualized learning for interpretable hierarchical representations of visual patterns" @default.
- W3080147302 cites W1486046602 @default.
- W3080147302 cites W1666926607 @default.
- W3080147302 cites W1941052021 @default.
- W3080147302 cites W1992613346 @default.
- W3080147302 cites W2002652493 @default.
- W3080147302 cites W2015861736 @default.
- W3080147302 cites W2019713466 @default.
- W3080147302 cites W2021443299 @default.
- W3080147302 cites W2031489346 @default.
- W3080147302 cites W2040446408 @default.
- W3080147302 cites W2051876768 @default.
- W3080147302 cites W2056814726 @default.
- W3080147302 cites W2088021044 @default.
- W3080147302 cites W2091434475 @default.
- W3080147302 cites W2098332664 @default.
- W3080147302 cites W2104853375 @default.
- W3080147302 cites W2105807774 @default.
- W3080147302 cites W2111605945 @default.
- W3080147302 cites W2115823588 @default.
- W3080147302 cites W2116360511 @default.
- W3080147302 cites W2117539524 @default.
- W3080147302 cites W2121029960 @default.
- W3080147302 cites W2151103935 @default.
- W3080147302 cites W2163922914 @default.
- W3080147302 cites W2259909269 @default.
- W3080147302 cites W2322893097 @default.
- W3080147302 cites W2331128040 @default.
- W3080147302 cites W2417219246 @default.
- W3080147302 cites W2502370765 @default.
- W3080147302 cites W2618608106 @default.
- W3080147302 cites W2746560897 @default.
- W3080147302 cites W2752782242 @default.
- W3080147302 cites W2762551375 @default.
- W3080147302 cites W2795309839 @default.
- W3080147302 cites W2805295533 @default.
- W3080147302 cites W2811106513 @default.
- W3080147302 cites W2884644855 @default.
- W3080147302 cites W2887114371 @default.
- W3080147302 cites W2889664156 @default.
- W3080147302 cites W2893201996 @default.
- W3080147302 cites W2900936384 @default.
- W3080147302 cites W2910021841 @default.
- W3080147302 cites W2941352015 @default.
- W3080147302 cites W2952956973 @default.
- W3080147302 cites W2961176043 @default.
- W3080147302 cites W2963037989 @default.
- W3080147302 cites W2963253279 @default.
- W3080147302 cites W2963816449 @default.
- W3080147302 cites W2963920537 @default.
- W3080147302 cites W2972308165 @default.
- W3080147302 cites W2993697375 @default.
- W3080147302 cites W2996141621 @default.
- W3080147302 cites W3005539111 @default.
- W3080147302 cites W3009709456 @default.
- W3080147302 cites W4238828427 @default.
- W3080147302 cites W4240266103 @default.
- W3080147302 cites W4251678559 @default.
- W3080147302 cites W4254587404 @default.
- W3080147302 cites W4255673801 @default.
- W3080147302 cites W4256293241 @default.
- W3080147302 doi "https://doi.org/10.1101/2020.08.25.266593" @default.
- W3080147302 hasPublicationYear "2020" @default.
- W3080147302 type Work @default.
- W3080147302 sameAs 3080147302 @default.
- W3080147302 citedByCount "0" @default.
- W3080147302 crossrefType "posted-content" @default.
- W3080147302 hasAuthorship W3080147302A5031215616 @default.
- W3080147302 hasAuthorship W3080147302A5033076875 @default.
- W3080147302 hasAuthorship W3080147302A5034127832 @default.
- W3080147302 hasBestOaLocation W30801473021 @default.
- W3080147302 hasConcept C119857082 @default.
- W3080147302 hasConcept C154945302 @default.
- W3080147302 hasConcept C15744967 @default.
- W3080147302 hasConcept C167966045 @default.
- W3080147302 hasConcept C177264268 @default.
- W3080147302 hasConcept C17744445 @default.
- W3080147302 hasConcept C199360897 @default.
- W3080147302 hasConcept C199539241 @default.
- W3080147302 hasConcept C2776214188 @default.
- W3080147302 hasConcept C2776359362 @default.
- W3080147302 hasConcept C39890363 @default.
- W3080147302 hasConcept C41008148 @default.
- W3080147302 hasConcept C49020025 @default.
- W3080147302 hasConcept C542102704 @default.
- W3080147302 hasConcept C94625758 @default.
- W3080147302 hasConcept C97931131 @default.
- W3080147302 hasConceptScore W3080147302C119857082 @default.
- W3080147302 hasConceptScore W3080147302C154945302 @default.
- W3080147302 hasConceptScore W3080147302C15744967 @default.
- W3080147302 hasConceptScore W3080147302C167966045 @default.
- W3080147302 hasConceptScore W3080147302C177264268 @default.
- W3080147302 hasConceptScore W3080147302C17744445 @default.