FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2996477650> ?p ?o ?g. }

• W2996477650 abstract "The long-timescale behavior of complex dynamical systems can be described by linear Markov or Koopman models in a suitable latent space. Recent variational approaches allow the latent space representation and the linear dynamical model to be optimized via unsupervised machine learning methods. Incorporation of physical constraints such as time-reversibility or stochasticity into the dynamical model has been established for a linear, but not for arbitrarily nonlinear (deep learning) representations of the latent space. Here we develop theory and methods for deep learning Markov and Koopman models that can bear such physical constraints. We prove that the model is an universal approximator for reversible Markov processes and that it can be optimized with either maximum likelihood or the variational approach of Markov processes (VAMP). We demonstrate that the model performs equally well for equilibrium and systematically better for biased data compared to existing approaches, thus providing a tool to study the long-timescale processes of dynamical systems." @default.
• W2996477650 created "2019-12-26" @default.
• W2996477650 creator A5014208179 @default.
• W2996477650 creator A5035236597 @default.
• W2996477650 creator A5055016850 @default.
• W2996477650 creator A5060090190 @default.
• W2996477650 date "2019-12-16" @default.
• W2996477650 modified "2023-09-27" @default.
• W2996477650 title "Deep learning Markov and Koopman models with physical constraints" @default.
• W2996477650 cites W1743379129 @default.
• W2996477650 cites W1977838033 @default.
• W2996477650 cites W1978607920 @default.
• W2996477650 cites W1979070806 @default.
• W2996477650 cites W1981889785 @default.
• W2996477650 cites W1984568974 @default.
• W2996477650 cites W1984649631 @default.
• W2996477650 cites W1989544083 @default.
• W2996477650 cites W1993299912 @default.
• W2996477650 cites W1997054581 @default.
• W2996477650 cites W2013638340 @default.
• W2996477650 cites W2014356541 @default.
• W2996477650 cites W2031843459 @default.
• W2996477650 cites W2046290306 @default.
• W2996477650 cites W2046898277 @default.
• W2996477650 cites W2053348581 @default.
• W2996477650 cites W2055484248 @default.
• W2996477650 cites W2056211671 @default.
• W2996477650 cites W2062421175 @default.
• W2996477650 cites W2065281489 @default.
• W2996477650 cites W2067035505 @default.
• W2996477650 cites W2072290134 @default.
• W2996477650 cites W2077933344 @default.
• W2996477650 cites W2081645999 @default.
• W2996477650 cites W2085213650 @default.
• W2996477650 cites W2088647884 @default.
• W2996477650 cites W2090500441 @default.
• W2996477650 cites W2091707670 @default.
• W2996477650 cites W2111339528 @default.
• W2996477650 cites W2122664326 @default.
• W2996477650 cites W2126999002 @default.
• W2996477650 cites W2133620840 @default.
• W2996477650 cites W2137595289 @default.
• W2996477650 cites W2141204324 @default.
• W2996477650 cites W2144134437 @default.
• W2996477650 cites W2164954534 @default.
• W2996477650 cites W2239232218 @default.
• W2996477650 cites W2249325510 @default.
• W2996477650 cites W2296686360 @default.
• W2996477650 cites W2315297180 @default.
• W2996477650 cites W2397367200 @default.
• W2996477650 cites W2483568213 @default.
• W2996477650 cites W2528583500 @default.
• W2996477650 cites W2591704465 @default.
• W2996477650 cites W2595314721 @default.
• W2996477650 cites W2736124076 @default.
• W2996477650 cites W2954046734 @default.
• W2996477650 cites W2963405490 @default.
• W2996477650 cites W2963426504 @default.
• W2996477650 cites W2964121744 @default.
• W2996477650 cites W2964129632 @default.
• W2996477650 cites W2964149432 @default.
• W2996477650 cites W2964917500 @default.
• W2996477650 cites W3099026129 @default.
• W2996477650 cites W3099245682 @default.
• W2996477650 cites W3099423575 @default.
• W2996477650 cites W3099803807 @default.
• W2996477650 cites W3101449947 @default.
• W2996477650 cites W3101619775 @default.
• W2996477650 cites W3105282846 @default.
• W2996477650 hasPublicationYear "2019" @default.
• W2996477650 type Work @default.
• W2996477650 sameAs 2996477650 @default.
• W2996477650 citedByCount "2" @default.
• W2996477650 countsByYear W29964776502020 @default.
• W2996477650 countsByYear W29964776502021 @default.
• W2996477650 crossrefType "posted-content" @default.
• W2996477650 hasAuthorship W2996477650A5014208179 @default.
• W2996477650 hasAuthorship W2996477650A5035236597 @default.
• W2996477650 hasAuthorship W2996477650A5055016850 @default.
• W2996477650 hasAuthorship W2996477650A5060090190 @default.
• W2996477650 hasConcept C105795698 @default.
• W2996477650 hasConcept C111919701 @default.
• W2996477650 hasConcept C116672817 @default.
• W2996477650 hasConcept C119857082 @default.
• W2996477650 hasConcept C121332964 @default.
• W2996477650 hasConcept C154945302 @default.
• W2996477650 hasConcept C158622935 @default.
• W2996477650 hasConcept C159886148 @default.
• W2996477650 hasConcept C163836022 @default.
• W2996477650 hasConcept C17744445 @default.
• W2996477650 hasConcept C199539241 @default.
• W2996477650 hasConcept C2776359362 @default.
• W2996477650 hasConcept C2778572836 @default.
• W2996477650 hasConcept C33923547 @default.
• W2996477650 hasConcept C41008148 @default.
• W2996477650 hasConcept C62520636 @default.
• W2996477650 hasConcept C79379906 @default.
• W2996477650 hasConcept C94625758 @default.
• W2996477650 hasConcept C98763669 @default.
• W2996477650 hasConceptScore W2996477650C105795698 @default.

• next