Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297436302> ?p ?o ?g. }
Showing items 1 to 47 of
47
with 100 items per page.
- W4297436302 abstract "Scientists often use observational time series data to study complex natural processes, but regression analyses often assume simplistic dynamics. Recent advances in deep learning have yielded startling improvements to the performance of models of complex processes, but deep learning is generally not used for scientific analysis. Here we show that deep learning can be used to analyze complex processes, providing flexible function approximation while preserving interpretability. Our approach relaxes standard simplifying assumptions (e.g., linearity, stationarity, and homoscedasticity) that are implausible for many natural systems and may critically affect the interpretation of data. We evaluate our model on incremental human language processing, a domain with complex continuous dynamics. We demonstrate substantial improvements on behavioral and neuroimaging data, and we show that our model enables discovery of novel patterns in exploratory analyses, controls for diverse confounds in confirmatory analyses, and opens up research questions that are otherwise hard to study." @default.
- W4297436302 created "2022-09-28" @default.
- W4297436302 creator A5033058937 @default.
- W4297436302 creator A5086362177 @default.
- W4297436302 date "2022-09-24" @default.
- W4297436302 modified "2023-10-04" @default.
- W4297436302 title "A Deep Learning Approach to Analyzing Continuous-Time Systems" @default.
- W4297436302 doi "https://doi.org/10.48550/arxiv.2209.12128" @default.
- W4297436302 hasPublicationYear "2022" @default.
- W4297436302 type Work @default.
- W4297436302 citedByCount "0" @default.
- W4297436302 crossrefType "posted-content" @default.
- W4297436302 hasAuthorship W4297436302A5033058937 @default.
- W4297436302 hasAuthorship W4297436302A5086362177 @default.
- W4297436302 hasBestOaLocation W42974363021 @default.
- W4297436302 hasConcept C101104100 @default.
- W4297436302 hasConcept C104409967 @default.
- W4297436302 hasConcept C108583219 @default.
- W4297436302 hasConcept C119857082 @default.
- W4297436302 hasConcept C154945302 @default.
- W4297436302 hasConcept C2522767166 @default.
- W4297436302 hasConcept C2781067378 @default.
- W4297436302 hasConcept C41008148 @default.
- W4297436302 hasConceptScore W4297436302C101104100 @default.
- W4297436302 hasConceptScore W4297436302C104409967 @default.
- W4297436302 hasConceptScore W4297436302C108583219 @default.
- W4297436302 hasConceptScore W4297436302C119857082 @default.
- W4297436302 hasConceptScore W4297436302C154945302 @default.
- W4297436302 hasConceptScore W4297436302C2522767166 @default.
- W4297436302 hasConceptScore W4297436302C2781067378 @default.
- W4297436302 hasConceptScore W4297436302C41008148 @default.
- W4297436302 hasLocation W42974363021 @default.
- W4297436302 hasOpenAccess W4297436302 @default.
- W4297436302 hasPrimaryLocation W42974363021 @default.
- W4297436302 hasRelatedWork W3006943036 @default.
- W4297436302 hasRelatedWork W3129898729 @default.
- W4297436302 hasRelatedWork W4206534706 @default.
- W4297436302 hasRelatedWork W4229079080 @default.
- W4297436302 hasRelatedWork W4299487748 @default.
- W4297436302 hasRelatedWork W4310880831 @default.
- W4297436302 hasRelatedWork W4380075502 @default.
- W4297436302 hasRelatedWork W4385957992 @default.
- W4297436302 hasRelatedWork W4385965371 @default.
- W4297436302 hasRelatedWork W4386025632 @default.
- W4297436302 isParatext "false" @default.
- W4297436302 isRetracted "false" @default.
- W4297436302 workType "article" @default.