Matches in SemOpenAlex for { <https://semopenalex.org/work/W2953242300> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2953242300 abstract "Abstract Many real-world data sets, especially in biology, are produced by highly multivariate and nonlinear complex dynamical systems. In this paper, we focus on brain imaging data, including both calcium imaging and functional MRI data. Standard vector-autoregressive models are limited by their linearity assumptions, while nonlinear general-purpose, large-scale temporal models, such as LSTM networks, typically require large amounts of training data, not always readily available in biological applications; furthermore, such models have limited interpretability. We introduce here a novel approach for learning a nonlinear differential equation model aimed at capturing brain dynamics. Specifically, we propose a variable-projection optimization approach to estimate the parameters of the multivariate (coupled) van der Pol oscillator, and demonstrate that such a model can accurately represent nonlinear dynamics of the brain data. Furthermore, in order to improve the predictive accuracy when forecasting future brain-activity time series, we use this analytical model as an unlimited source of simulated data for pretraining LSTM; such model-specific data augmentation approach consistently improves LSTM performance on both calcium and fMRI imaging data." @default.
- W2953242300 created "2019-06-27" @default.
- W2953242300 creator A5010323219 @default.
- W2953242300 creator A5055430458 @default.
- W2953242300 creator A5065396462 @default.
- W2953242300 creator A5070547937 @default.
- W2953242300 creator A5072154999 @default.
- W2953242300 creator A5078547686 @default.
- W2953242300 creator A5091863515 @default.
- W2953242300 date "2018-05-25" @default.
- W2953242300 modified "2023-10-04" @default.
- W2953242300 title "Learning Nonlinear Brain Dynamics: van der Pol Meets LSTM" @default.
- W2953242300 cites W1179800764 @default.
- W2953242300 cites W1576838367 @default.
- W2953242300 cites W1600765471 @default.
- W2953242300 cites W1847315806 @default.
- W2953242300 cites W1964248020 @default.
- W2953242300 cites W1986294597 @default.
- W2953242300 cites W1986842884 @default.
- W2953242300 cites W1997462664 @default.
- W2953242300 cites W2009375605 @default.
- W2953242300 cites W2016765436 @default.
- W2953242300 cites W2030105977 @default.
- W2953242300 cites W2064675550 @default.
- W2953242300 cites W2083402998 @default.
- W2953242300 cites W2084771878 @default.
- W2953242300 cites W2089315051 @default.
- W2953242300 cites W2109455849 @default.
- W2953242300 cites W2114714448 @default.
- W2953242300 cites W2125923236 @default.
- W2953242300 cites W2134266087 @default.
- W2953242300 cites W2156435365 @default.
- W2953242300 cites W2963638855 @default.
- W2953242300 cites W2963869366 @default.
- W2953242300 cites W2964061302 @default.
- W2953242300 doi "https://doi.org/10.1101/330548" @default.
- W2953242300 hasPublicationYear "2018" @default.
- W2953242300 type Work @default.
- W2953242300 sameAs 2953242300 @default.
- W2953242300 citedByCount "2" @default.
- W2953242300 countsByYear W29532423002020 @default.
- W2953242300 countsByYear W29532423002022 @default.
- W2953242300 crossrefType "posted-content" @default.
- W2953242300 hasAuthorship W2953242300A5010323219 @default.
- W2953242300 hasAuthorship W2953242300A5055430458 @default.
- W2953242300 hasAuthorship W2953242300A5065396462 @default.
- W2953242300 hasAuthorship W2953242300A5070547937 @default.
- W2953242300 hasAuthorship W2953242300A5072154999 @default.
- W2953242300 hasAuthorship W2953242300A5078547686 @default.
- W2953242300 hasAuthorship W2953242300A5091863515 @default.
- W2953242300 hasBestOaLocation W29532423001 @default.
- W2953242300 hasConcept C119857082 @default.
- W2953242300 hasConcept C121332964 @default.
- W2953242300 hasConcept C149782125 @default.
- W2953242300 hasConcept C151406439 @default.
- W2953242300 hasConcept C154945302 @default.
- W2953242300 hasConcept C158622935 @default.
- W2953242300 hasConcept C159877910 @default.
- W2953242300 hasConcept C2781067378 @default.
- W2953242300 hasConcept C33923547 @default.
- W2953242300 hasConcept C41008148 @default.
- W2953242300 hasConcept C62520636 @default.
- W2953242300 hasConcept C98010927 @default.
- W2953242300 hasConceptScore W2953242300C119857082 @default.
- W2953242300 hasConceptScore W2953242300C121332964 @default.
- W2953242300 hasConceptScore W2953242300C149782125 @default.
- W2953242300 hasConceptScore W2953242300C151406439 @default.
- W2953242300 hasConceptScore W2953242300C154945302 @default.
- W2953242300 hasConceptScore W2953242300C158622935 @default.
- W2953242300 hasConceptScore W2953242300C159877910 @default.
- W2953242300 hasConceptScore W2953242300C2781067378 @default.
- W2953242300 hasConceptScore W2953242300C33923547 @default.
- W2953242300 hasConceptScore W2953242300C41008148 @default.
- W2953242300 hasConceptScore W2953242300C62520636 @default.
- W2953242300 hasConceptScore W2953242300C98010927 @default.
- W2953242300 hasLocation W29532423001 @default.
- W2953242300 hasLocation W29532423002 @default.
- W2953242300 hasOpenAccess W2953242300 @default.
- W2953242300 hasPrimaryLocation W29532423001 @default.
- W2953242300 hasRelatedWork W2991396638 @default.
- W2953242300 hasRelatedWork W3006943036 @default.
- W2953242300 hasRelatedWork W3012234327 @default.
- W2953242300 hasRelatedWork W3119715496 @default.
- W2953242300 hasRelatedWork W3191046242 @default.
- W2953242300 hasRelatedWork W3203961807 @default.
- W2953242300 hasRelatedWork W3214185682 @default.
- W2953242300 hasRelatedWork W4206534706 @default.
- W2953242300 hasRelatedWork W4229079080 @default.
- W2953242300 hasRelatedWork W4294031299 @default.
- W2953242300 isParatext "false" @default.
- W2953242300 isRetracted "false" @default.
- W2953242300 magId "2953242300" @default.
- W2953242300 workType "article" @default.