Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209716417> ?p ?o ?g. }
- W3209716417 abstract "Deep neural networks have become increasingly of interest in dynamical system prediction, but out-of-distribution generalization and long-term stability still remains challenging. In this work, we treat the domain parameters of dynamical systems as factors of variation of the data generating process. By leveraging ideas from supervised disentanglement and causal factorization, we aim to separate the domain parameters from the dynamics in the latent space of generative models. In our experiments we model dynamics both in phase space and in video sequences and conduct rigorous OOD evaluations. Results indicate that disentangled VAEs adapt better to domain parameters spaces that were not present in the training data. At the same time, disentanglement can improve the long-term and out-of-distribution predictions of state-of-the-art models in video sequences." @default.
- W3209716417 created "2021-11-08" @default.
- W3209716417 creator A5011415013 @default.
- W3209716417 creator A5012705709 @default.
- W3209716417 creator A5024813114 @default.
- W3209716417 creator A5027222571 @default.
- W3209716417 creator A5053809263 @default.
- W3209716417 date "2021-08-26" @default.
- W3209716417 modified "2023-09-26" @default.
- W3209716417 title "Disentangled generative models for robust dynamical system prediction" @default.
- W3209716417 cites W1959608418 @default.
- W3209716417 cites W2163922914 @default.
- W3209716417 cites W2753738274 @default.
- W3209716417 cites W2808697642 @default.
- W3209716417 cites W2884775584 @default.
- W3209716417 cites W2899283552 @default.
- W3209716417 cites W2900152462 @default.
- W3209716417 cites W2903538854 @default.
- W3209716417 cites W2905204718 @default.
- W3209716417 cites W2944851425 @default.
- W3209716417 cites W2951392118 @default.
- W3209716417 cites W2962785568 @default.
- W3209716417 cites W2962864714 @default.
- W3209716417 cites W2963104724 @default.
- W3209716417 cites W2963166838 @default.
- W3209716417 cites W2963618559 @default.
- W3209716417 cites W2964145160 @default.
- W3209716417 cites W2971162686 @default.
- W3209716417 cites W3016894691 @default.
- W3209716417 cites W3082851515 @default.
- W3209716417 cites W3093010610 @default.
- W3209716417 cites W3101442004 @default.
- W3209716417 cites W3108981297 @default.
- W3209716417 cites W3111507638 @default.
- W3209716417 cites W3132648081 @default.
- W3209716417 cites W3139190393 @default.
- W3209716417 cites W3145849805 @default.
- W3209716417 cites W3164915304 @default.
- W3209716417 cites W3202525453 @default.
- W3209716417 cites W3202670046 @default.
- W3209716417 hasPublicationYear "2021" @default.
- W3209716417 type Work @default.
- W3209716417 sameAs 3209716417 @default.
- W3209716417 citedByCount "0" @default.
- W3209716417 crossrefType "posted-content" @default.
- W3209716417 hasAuthorship W3209716417A5011415013 @default.
- W3209716417 hasAuthorship W3209716417A5012705709 @default.
- W3209716417 hasAuthorship W3209716417A5024813114 @default.
- W3209716417 hasAuthorship W3209716417A5027222571 @default.
- W3209716417 hasAuthorship W3209716417A5053809263 @default.
- W3209716417 hasConcept C105795698 @default.
- W3209716417 hasConcept C111919701 @default.
- W3209716417 hasConcept C112972136 @default.
- W3209716417 hasConcept C119857082 @default.
- W3209716417 hasConcept C121332964 @default.
- W3209716417 hasConcept C134306372 @default.
- W3209716417 hasConcept C151342819 @default.
- W3209716417 hasConcept C154945302 @default.
- W3209716417 hasConcept C167966045 @default.
- W3209716417 hasConcept C177148314 @default.
- W3209716417 hasConcept C33923547 @default.
- W3209716417 hasConcept C36503486 @default.
- W3209716417 hasConcept C39890363 @default.
- W3209716417 hasConcept C41008148 @default.
- W3209716417 hasConcept C61797465 @default.
- W3209716417 hasConcept C62520636 @default.
- W3209716417 hasConcept C72434380 @default.
- W3209716417 hasConcept C79379906 @default.
- W3209716417 hasConcept C97355855 @default.
- W3209716417 hasConcept C98045186 @default.
- W3209716417 hasConceptScore W3209716417C105795698 @default.
- W3209716417 hasConceptScore W3209716417C111919701 @default.
- W3209716417 hasConceptScore W3209716417C112972136 @default.
- W3209716417 hasConceptScore W3209716417C119857082 @default.
- W3209716417 hasConceptScore W3209716417C121332964 @default.
- W3209716417 hasConceptScore W3209716417C134306372 @default.
- W3209716417 hasConceptScore W3209716417C151342819 @default.
- W3209716417 hasConceptScore W3209716417C154945302 @default.
- W3209716417 hasConceptScore W3209716417C167966045 @default.
- W3209716417 hasConceptScore W3209716417C177148314 @default.
- W3209716417 hasConceptScore W3209716417C33923547 @default.
- W3209716417 hasConceptScore W3209716417C36503486 @default.
- W3209716417 hasConceptScore W3209716417C39890363 @default.
- W3209716417 hasConceptScore W3209716417C41008148 @default.
- W3209716417 hasConceptScore W3209716417C61797465 @default.
- W3209716417 hasConceptScore W3209716417C62520636 @default.
- W3209716417 hasConceptScore W3209716417C72434380 @default.
- W3209716417 hasConceptScore W3209716417C79379906 @default.
- W3209716417 hasConceptScore W3209716417C97355855 @default.
- W3209716417 hasConceptScore W3209716417C98045186 @default.
- W3209716417 hasLocation W32097164171 @default.
- W3209716417 hasOpenAccess W3209716417 @default.
- W3209716417 hasPrimaryLocation W32097164171 @default.
- W3209716417 hasRelatedWork W1686011160 @default.
- W3209716417 hasRelatedWork W2070513006 @default.
- W3209716417 hasRelatedWork W2171627535 @default.
- W3209716417 hasRelatedWork W2185095271 @default.
- W3209716417 hasRelatedWork W2405672565 @default.
- W3209716417 hasRelatedWork W2623055298 @default.
- W3209716417 hasRelatedWork W2792943806 @default.