Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100181198> ?p ?o ?g. }
- W3100181198 abstract "Time-lagged autoencoders (TAEs) have been proposed as a deep learning regression-based approach to the discovery of slow modes in dynamical systems. However, a rigorous analysis of nonlinear TAEs remains lacking. In this work, we discuss the capabilities and limitations of TAEs through both theoretical and numerical analyses. Theoretically, we derive bounds for nonlinear TAE performance in slow mode discovery and show that in general TAEs learn a mixture of slow and maximum variance modes. Numerically, we illustrate cases where TAEs can and cannot correctly identify the leading slowest mode in two example systems: a 2D Washington beltway potential and the alanine dipeptide molecule in explicit water. We also compare the TAE results with those obtained using state-free reversible VAMPnets (SRVs) as a variational-based neural network approach for slow modes discovery, and show that SRVs can correctly discover slow modes where TAEs fail." @default.
- W3100181198 created "2020-11-23" @default.
- W3100181198 creator A5017541508 @default.
- W3100181198 creator A5023302612 @default.
- W3100181198 creator A5024146798 @default.
- W3100181198 date "2019-08-14" @default.
- W3100181198 modified "2023-10-14" @default.
- W3100181198 title "Capabilities and limitations of time-lagged autoencoders for slow mode discovery in dynamical systems" @default.
- W3100181198 cites W1976203248 @default.
- W3100181198 cites W1976499671 @default.
- W3100181198 cites W1978189250 @default.
- W3100181198 cites W1989544083 @default.
- W3100181198 cites W1997054581 @default.
- W3100181198 cites W1999670894 @default.
- W3100181198 cites W2025341678 @default.
- W3100181198 cites W2029667189 @default.
- W3100181198 cites W2035687084 @default.
- W3100181198 cites W2036682095 @default.
- W3100181198 cites W2046898277 @default.
- W3100181198 cites W2065281489 @default.
- W3100181198 cites W2067035505 @default.
- W3100181198 cites W2067076385 @default.
- W3100181198 cites W2080991705 @default.
- W3100181198 cites W2085213650 @default.
- W3100181198 cites W2139923370 @default.
- W3100181198 cites W2160341881 @default.
- W3100181198 cites W2161605421 @default.
- W3100181198 cites W2315297180 @default.
- W3100181198 cites W2528583500 @default.
- W3100181198 cites W2540372843 @default.
- W3100181198 cites W2561027863 @default.
- W3100181198 cites W2570547882 @default.
- W3100181198 cites W2594932112 @default.
- W3100181198 cites W2757258616 @default.
- W3100181198 cites W2765861397 @default.
- W3100181198 cites W2768480811 @default.
- W3100181198 cites W2782714865 @default.
- W3100181198 cites W2783073729 @default.
- W3100181198 cites W2793316145 @default.
- W3100181198 cites W2889143727 @default.
- W3100181198 cites W2899667845 @default.
- W3100181198 cites W2903246169 @default.
- W3100181198 cites W2949223833 @default.
- W3100181198 cites W2954046734 @default.
- W3100181198 cites W2962959797 @default.
- W3100181198 cites W2963393681 @default.
- W3100181198 cites W2963426504 @default.
- W3100181198 cites W2964129632 @default.
- W3100181198 cites W2964149432 @default.
- W3100181198 cites W3098732481 @default.
- W3100181198 cites W3099205493 @default.
- W3100181198 cites W3099423575 @default.
- W3100181198 cites W3100810942 @default.
- W3100181198 doi "https://doi.org/10.1063/1.5112048" @default.
- W3100181198 hasPublicationYear "2019" @default.
- W3100181198 type Work @default.
- W3100181198 sameAs 3100181198 @default.
- W3100181198 citedByCount "28" @default.
- W3100181198 countsByYear W31001811982019 @default.
- W3100181198 countsByYear W31001811982020 @default.
- W3100181198 countsByYear W31001811982021 @default.
- W3100181198 countsByYear W31001811982022 @default.
- W3100181198 countsByYear W31001811982023 @default.
- W3100181198 crossrefType "journal-article" @default.
- W3100181198 hasAuthorship W3100181198A5017541508 @default.
- W3100181198 hasAuthorship W3100181198A5023302612 @default.
- W3100181198 hasAuthorship W3100181198A5024146798 @default.
- W3100181198 hasBestOaLocation W31001811981 @default.
- W3100181198 hasConcept C108583219 @default.
- W3100181198 hasConcept C111919701 @default.
- W3100181198 hasConcept C121332964 @default.
- W3100181198 hasConcept C121864883 @default.
- W3100181198 hasConcept C154945302 @default.
- W3100181198 hasConcept C158622935 @default.
- W3100181198 hasConcept C2984842247 @default.
- W3100181198 hasConcept C41008148 @default.
- W3100181198 hasConcept C48677424 @default.
- W3100181198 hasConcept C50644808 @default.
- W3100181198 hasConcept C62520636 @default.
- W3100181198 hasConcept C79379906 @default.
- W3100181198 hasConceptScore W3100181198C108583219 @default.
- W3100181198 hasConceptScore W3100181198C111919701 @default.
- W3100181198 hasConceptScore W3100181198C121332964 @default.
- W3100181198 hasConceptScore W3100181198C121864883 @default.
- W3100181198 hasConceptScore W3100181198C154945302 @default.
- W3100181198 hasConceptScore W3100181198C158622935 @default.
- W3100181198 hasConceptScore W3100181198C2984842247 @default.
- W3100181198 hasConceptScore W3100181198C41008148 @default.
- W3100181198 hasConceptScore W3100181198C48677424 @default.
- W3100181198 hasConceptScore W3100181198C50644808 @default.
- W3100181198 hasConceptScore W3100181198C62520636 @default.
- W3100181198 hasConceptScore W3100181198C79379906 @default.
- W3100181198 hasFunder F4320306076 @default.
- W3100181198 hasIssue "6" @default.
- W3100181198 hasLocation W31001811981 @default.
- W3100181198 hasLocation W31001811982 @default.
- W3100181198 hasLocation W31001811983 @default.
- W3100181198 hasOpenAccess W3100181198 @default.
- W3100181198 hasPrimaryLocation W31001811981 @default.
- W3100181198 hasRelatedWork W2611989081 @default.