FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3207062011> ?p ?o ?g. }

• W3207062011 abstract "Neuroscience has seen a dramatic increase in the types of recording modalities and complexity of neural time-series data collected from them. The brain is a highly recurrent system producing rich, complex dynamics that result in different behaviors. Correctly distinguishing such nonlinear neural time series in real-time, especially those with non-obvious links to behavior, could be useful for a wide variety of applications. These include detecting anomalous clinical events such as seizures in epilepsy, and identifying optimal control spaces for brain machine interfaces. It remains challenging to correctly distinguish nonlinear time-series patterns because of the high intrinsic dimensionality of such data, making accurate inference of state changes (for intervention or control) difficult. Simple distance metrics, which can be computed quickly do not yield accurate classifications. On the other end of the spectrum of classification methods, ensembles of classifiers or deep supervised tools offer higher accuracy but are slow, data-intensive, and computationally expensive. We introduce a reservoir-based tool, state tracker (TRAKR), which offers the high accuracy of ensembles or deep supervised methods while preserving the computational benefits of simple distance metrics. After one-shot training, TRAKR can accurately, and in real time, detect deviations in test patterns. By forcing the weighted dynamics of the reservoir to fit a desired pattern directly, we avoid many rounds of expensive optimization. Then, keeping the output weights frozen, we use the error signal generated by the reservoir in response to a particular test pattern as a classification boundary. We show that, using this approach, TRAKR accurately detects changes in synthetic time series. We then compare our tool to several others, showing that it achieves highest classification performance on a benchmark dataset, sequential MNIST, even when corrupted by noise. Additionally, we apply TRAKR to electrocorticography (ECoG) data from the macaque orbitofrontal cortex (OFC), a higher-order brain region involved in encoding the value of expected outcomes. We show that TRAKR can classify different behaviorally relevant epochs in the neural time series more accurately and efficiently than conventional approaches. Therefore, TRAKR can be used as a fast and accurate tool to distinguish patterns in complex nonlinear time-series data, such as neural recordings." @default.
• W3207062011 created "2021-10-25" @default.
• W3207062011 creator A5010289380 @default.
• W3207062011 creator A5062769900 @default.
• W3207062011 creator A5070167718 @default.
• W3207062011 creator A5091491816 @default.
• W3207062011 date "2021-10-15" @default.
• W3207062011 modified "2023-10-15" @default.
• W3207062011 title "TRAKR - A reservoir-based tool for fast and accurate classification of neural time-series patterns" @default.
• W3207062011 cites W1482139424 @default.
• W3207062011 cites W1492221128 @default.
• W3207062011 cites W152645600 @default.
• W3207062011 cites W1572445695 @default.
• W3207062011 cites W1800356822 @default.
• W3207062011 cites W1969923483 @default.
• W3207062011 cites W1971567789 @default.
• W3207062011 cites W1979152481 @default.
• W3207062011 cites W1991097067 @default.
• W3207062011 cites W1997102766 @default.
• W3207062011 cites W2025054170 @default.
• W3207062011 cites W2035104901 @default.
• W3207062011 cites W2036146020 @default.
• W3207062011 cites W2038593423 @default.
• W3207062011 cites W2047125104 @default.
• W3207062011 cites W2058978266 @default.
• W3207062011 cites W2060351760 @default.
• W3207062011 cites W2066515711 @default.
• W3207062011 cites W2090157379 @default.
• W3207062011 cites W2099231026 @default.
• W3207062011 cites W2102201884 @default.
• W3207062011 cites W2102701721 @default.
• W3207062011 cites W2103179919 @default.
• W3207062011 cites W2124780821 @default.
• W3207062011 cites W2139461681 @default.
• W3207062011 cites W2144994235 @default.
• W3207062011 cites W2150354929 @default.
• W3207062011 cites W2170476476 @default.
• W3207062011 cites W2295845209 @default.
• W3207062011 cites W2295972917 @default.
• W3207062011 cites W2419461529 @default.
• W3207062011 cites W2510380565 @default.
• W3207062011 cites W2512532751 @default.
• W3207062011 cites W2561857267 @default.
• W3207062011 cites W2585354796 @default.
• W3207062011 cites W2600919610 @default.
• W3207062011 cites W2753368814 @default.
• W3207062011 cites W2782714865 @default.
• W3207062011 cites W2791136272 @default.
• W3207062011 cites W2800311957 @default.
• W3207062011 cites W2892035503 @default.
• W3207062011 cites W2894528679 @default.
• W3207062011 cites W2908124316 @default.
• W3207062011 cites W2949410666 @default.
• W3207062011 cites W2949938118 @default.
• W3207062011 cites W2951777958 @default.
• W3207062011 cites W2967821093 @default.
• W3207062011 cites W2970053421 @default.
• W3207062011 cites W2978368159 @default.
• W3207062011 cites W2988244882 @default.
• W3207062011 cites W3012621877 @default.
• W3207062011 cites W3080933029 @default.
• W3207062011 cites W3087710711 @default.
• W3207062011 cites W3199573619 @default.
• W3207062011 doi "https://doi.org/10.1101/2021.10.13.464288" @default.
• W3207062011 hasPublicationYear "2021" @default.
• W3207062011 type Work @default.
• W3207062011 sameAs 3207062011 @default.
• W3207062011 citedByCount "0" @default.
• W3207062011 crossrefType "posted-content" @default.
• W3207062011 hasAuthorship W3207062011A5010289380 @default.
• W3207062011 hasAuthorship W3207062011A5062769900 @default.
• W3207062011 hasAuthorship W3207062011A5070167718 @default.
• W3207062011 hasAuthorship W3207062011A5091491816 @default.
• W3207062011 hasBestOaLocation W32070620111 @default.
• W3207062011 hasConcept C111030470 @default.
• W3207062011 hasConcept C119857082 @default.
• W3207062011 hasConcept C135796866 @default.
• W3207062011 hasConcept C143724316 @default.
• W3207062011 hasConcept C147168706 @default.
• W3207062011 hasConcept C151406439 @default.
• W3207062011 hasConcept C151730666 @default.
• W3207062011 hasConcept C153180895 @default.
• W3207062011 hasConcept C154945302 @default.
• W3207062011 hasConcept C2776214188 @default.
• W3207062011 hasConcept C41008148 @default.
• W3207062011 hasConcept C50644808 @default.
• W3207062011 hasConcept C86803240 @default.
• W3207062011 hasConceptScore W3207062011C111030470 @default.
• W3207062011 hasConceptScore W3207062011C119857082 @default.
• W3207062011 hasConceptScore W3207062011C135796866 @default.
• W3207062011 hasConceptScore W3207062011C143724316 @default.
• W3207062011 hasConceptScore W3207062011C147168706 @default.
• W3207062011 hasConceptScore W3207062011C151406439 @default.
• W3207062011 hasConceptScore W3207062011C151730666 @default.
• W3207062011 hasConceptScore W3207062011C153180895 @default.
• W3207062011 hasConceptScore W3207062011C154945302 @default.
• W3207062011 hasConceptScore W3207062011C2776214188 @default.
• W3207062011 hasConceptScore W3207062011C41008148 @default.
• W3207062011 hasConceptScore W3207062011C50644808 @default.
• W3207062011 hasConceptScore W3207062011C86803240 @default.

• next