FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201539443> ?p ?o ?g. }

• W3201539443 abstract "Abstract Recent advances in neural decoding have accelerated the development of brain-computer interfaces aimed at assisting users with everyday tasks such as speaking, walking, and manipulating objects. However, current approaches for training neural decoders commonly require large quantities of labeled data, which can be laborious or infeasible to obtain in real-world settings. One intriguing alternative uses self-supervised models that share self-generated pseudo-labels between two data streams; such models have shown exceptional performance on unlabeled audio and video data, but it remains unclear how well they extend to neural decoding. Here, we learn neural decoders without labels by leveraging multiple simultaneously recorded data streams, including neural, kinematic, and physiological signals. Specifically, we apply cross-modal, self-supervised deep clustering to decode movements from brain recordings; these decoders are compared to supervised and unimodal, self-supervised models. We find that sharing pseudo-labels between two data streams during training substantially increases decoding performance compared to unimodal, self-supervised models, with accuracies approaching those of supervised decoders trained on labeled data. Next, we develop decoders trained on three modalities that match or slightly exceed the performance of supervised models, achieving state-of-the-art neural decoding accuracy. Cross-modal decoding is a flexible, promising approach for robust, adaptive neural decoding in real-world applications without any labels." @default.
• W3201539443 created "2021-09-27" @default.
• W3201539443 creator A5002759219 @default.
• W3201539443 creator A5027826197 @default.
• W3201539443 creator A5080171470 @default.
• W3201539443 date "2021-09-11" @default.
• W3201539443 modified "2023-09-27" @default.
• W3201539443 title "Learning neural decoders without labels using multiple data streams" @default.
• W3201539443 cites W1449283962 @default.
• W3201539443 cites W1619896805 @default.
• W3201539443 cites W1919077608 @default.
• W3201539443 cites W1974758710 @default.
• W3201539443 cites W1977204789 @default.
• W3201539443 cites W1980688411 @default.
• W3201539443 cites W2015119447 @default.
• W3201539443 cites W2040590444 @default.
• W3201539443 cites W2046633886 @default.
• W3201539443 cites W2064675550 @default.
• W3201539443 cites W2083488908 @default.
• W3201539443 cites W2102315587 @default.
• W3201539443 cites W2103275652 @default.
• W3201539443 cites W2115383940 @default.
• W3201539443 cites W2138372226 @default.
• W3201539443 cites W2148492655 @default.
• W3201539443 cites W2153035821 @default.
• W3201539443 cites W2170618918 @default.
• W3201539443 cites W2461769565 @default.
• W3201539443 cites W2518937691 @default.
• W3201539443 cites W2611568640 @default.
• W3201539443 cites W2622731166 @default.
• W3201539443 cites W2726388785 @default.
• W3201539443 cites W2742728815 @default.
• W3201539443 cites W2755020143 @default.
• W3201539443 cites W2770426008 @default.
• W3201539443 cites W2790652677 @default.
• W3201539443 cites W2790682483 @default.
• W3201539443 cites W2839867530 @default.
• W3201539443 cites W2883725317 @default.
• W3201539443 cites W2885971283 @default.
• W3201539443 cites W2891509242 @default.
• W3201539443 cites W2892295414 @default.
• W3201539443 cites W2898593582 @default.
• W3201539443 cites W2902242774 @default.
• W3201539443 cites W2902670861 @default.
• W3201539443 cites W2910825437 @default.
• W3201539443 cites W2922598768 @default.
• W3201539443 cites W2954952848 @default.
• W3201539443 cites W2962896355 @default.
• W3201539443 cites W2962982021 @default.
• W3201539443 cites W2964052309 @default.
• W3201539443 cites W2969808165 @default.
• W3201539443 cites W2987448886 @default.
• W3201539443 cites W2990604239 @default.
• W3201539443 cites W3016557315 @default.
• W3201539443 cites W3016977963 @default.
• W3201539443 cites W3018645360 @default.
• W3201539443 cites W3019103505 @default.
• W3201539443 cites W3023371261 @default.
• W3201539443 cites W3031024919 @default.
• W3201539443 cites W3040046878 @default.
• W3201539443 cites W3046474724 @default.
• W3201539443 cites W3046749939 @default.
• W3201539443 cites W3080427797 @default.
• W3201539443 cites W3084035636 @default.
• W3201539443 cites W3088058284 @default.
• W3201539443 cites W3101658985 @default.
• W3201539443 cites W3102455230 @default.
• W3201539443 cites W3110151578 @default.
• W3201539443 cites W3120583211 @default.
• W3201539443 cites W3158859144 @default.
• W3201539443 cites W3161143221 @default.
• W3201539443 cites W3173151551 @default.
• W3201539443 cites W3175308890 @default.
• W3201539443 cites W3180220247 @default.
• W3201539443 cites W3183272872 @default.
• W3201539443 cites W4210328736 @default.
• W3201539443 cites W4230797216 @default.
• W3201539443 doi "https://doi.org/10.1101/2021.09.10.459775" @default.
• W3201539443 hasPublicationYear "2021" @default.
• W3201539443 type Work @default.
• W3201539443 sameAs 3201539443 @default.
• W3201539443 citedByCount "3" @default.
• W3201539443 countsByYear W32015394432022 @default.
• W3201539443 crossrefType "posted-content" @default.
• W3201539443 hasAuthorship W3201539443A5002759219 @default.
• W3201539443 hasAuthorship W3201539443A5027826197 @default.
• W3201539443 hasAuthorship W3201539443A5080171470 @default.
• W3201539443 hasBestOaLocation W32015394431 @default.
• W3201539443 hasConcept C11413529 @default.
• W3201539443 hasConcept C119857082 @default.
• W3201539443 hasConcept C136389625 @default.
• W3201539443 hasConcept C144024400 @default.
• W3201539443 hasConcept C153180895 @default.
• W3201539443 hasConcept C154945302 @default.
• W3201539443 hasConcept C2776145971 @default.
• W3201539443 hasConcept C2779903281 @default.
• W3201539443 hasConcept C36289849 @default.
• W3201539443 hasConcept C40743351 @default.
• W3201539443 hasConcept C41008148 @default.
• W3201539443 hasConcept C50644808 @default.

• next