Matches in SemOpenAlex for { <https://semopenalex.org/work/W3096766006> ?p ?o ?g. }
- W3096766006 abstract "Abstract Objective Advances in neural decoding have enabled brain-computer interfaces to perform increasingly complex and clinically-relevant tasks. However, such decoders are often tailored to specific participants, days, and recording sites, limiting their practical long-term usage. Therefore, a fundamental challenge is to develop neural decoders that can robustly train on pooled, multi-participant data and generalize to new participants. Approach We introduce a new decoder, HTNet, which uses a convolutional neural network with two innovations: (1) a Hilbert transform that computes spectral power at data-driven frequencies and (2) a layer that projects electrode-level data onto predefined brain regions. The projection layer critically enables applications with intracranial electrocorticography (ECoG), where electrode locations are not standardized and vary widely across participants. We trained HTNet to decode arm movements using pooled ECoG data from 11 of 12 participants and tested performance on unseen ECoG or electroencephalography (EEG) participants; these pretrained models were also subsequently fine-tuned to each test participant. Main results HTNet outperformed state-of-the-art decoders when tested on unseen participants, even when a different recording modality was used. By fine-tuning these generalized HTNet decoders, we achieved performance approaching the best tailored decoders with as few as 50 ECoG or 20 EEG events. We were also able to interpret HTNet’s trained weights and demonstrate its ability to extract physiologically-relevant features. Significance By generalizing to new participants and recording modalities, robustly handling variations in electrode placement, and allowing participant-specific fine-tuning with minimal data, HTNet is applicable across a broader range of neural decoding applications compared to current state-of-the-art decoders." @default.
- W3096766006 created "2020-11-09" @default.
- W3096766006 creator A5002759219 @default.
- W3096766006 creator A5027826197 @default.
- W3096766006 creator A5033568778 @default.
- W3096766006 creator A5059199834 @default.
- W3096766006 creator A5080171470 @default.
- W3096766006 date "2020-11-02" @default.
- W3096766006 modified "2023-09-30" @default.
- W3096766006 title "Generalized neural decoders for transfer learning across participants and recording modalities" @default.
- W3096766006 cites W1619896805 @default.
- W3096766006 cites W1978389345 @default.
- W3096766006 cites W1981937980 @default.
- W3096766006 cites W2015119447 @default.
- W3096766006 cites W2015356304 @default.
- W3096766006 cites W2018440299 @default.
- W3096766006 cites W2020745232 @default.
- W3096766006 cites W2033869966 @default.
- W3096766006 cites W2051508348 @default.
- W3096766006 cites W2058046532 @default.
- W3096766006 cites W2067975977 @default.
- W3096766006 cites W2094572290 @default.
- W3096766006 cites W2102315587 @default.
- W3096766006 cites W2103275652 @default.
- W3096766006 cites W2105957367 @default.
- W3096766006 cites W2119223881 @default.
- W3096766006 cites W2128495200 @default.
- W3096766006 cites W2135825876 @default.
- W3096766006 cites W2141250485 @default.
- W3096766006 cites W2142501675 @default.
- W3096766006 cites W2155658404 @default.
- W3096766006 cites W2157725122 @default.
- W3096766006 cites W2168210093 @default.
- W3096766006 cites W2314733761 @default.
- W3096766006 cites W2388189391 @default.
- W3096766006 cites W2461769565 @default.
- W3096766006 cites W2539213780 @default.
- W3096766006 cites W2568766977 @default.
- W3096766006 cites W2602279467 @default.
- W3096766006 cites W2622731166 @default.
- W3096766006 cites W2726388785 @default.
- W3096766006 cites W2741907166 @default.
- W3096766006 cites W2755020143 @default.
- W3096766006 cites W2765161362 @default.
- W3096766006 cites W2770037632 @default.
- W3096766006 cites W2781449637 @default.
- W3096766006 cites W2782138411 @default.
- W3096766006 cites W2790682483 @default.
- W3096766006 cites W2792724009 @default.
- W3096766006 cites W2800156675 @default.
- W3096766006 cites W2884032402 @default.
- W3096766006 cites W2885971283 @default.
- W3096766006 cites W2891509242 @default.
- W3096766006 cites W2892295414 @default.
- W3096766006 cites W2901940453 @default.
- W3096766006 cites W2902670861 @default.
- W3096766006 cites W2909905004 @default.
- W3096766006 cites W2940585064 @default.
- W3096766006 cites W2949385804 @default.
- W3096766006 cites W2949676527 @default.
- W3096766006 cites W2951108876 @default.
- W3096766006 cites W2954952848 @default.
- W3096766006 cites W2962999323 @default.
- W3096766006 cites W2963000173 @default.
- W3096766006 cites W2963355311 @default.
- W3096766006 cites W2963752866 @default.
- W3096766006 cites W2963822470 @default.
- W3096766006 cites W2964019954 @default.
- W3096766006 cites W2969808165 @default.
- W3096766006 cites W2970750283 @default.
- W3096766006 cites W2980306787 @default.
- W3096766006 cites W2987448886 @default.
- W3096766006 cites W2994422921 @default.
- W3096766006 cites W3008011111 @default.
- W3096766006 cites W3012375271 @default.
- W3096766006 cites W3013691153 @default.
- W3096766006 cites W3016295717 @default.
- W3096766006 cites W3016557315 @default.
- W3096766006 cites W3016977963 @default.
- W3096766006 cites W3017642177 @default.
- W3096766006 cites W3018645360 @default.
- W3096766006 cites W3028375381 @default.
- W3096766006 cites W3028506176 @default.
- W3096766006 cites W3028668603 @default.
- W3096766006 cites W3040046878 @default.
- W3096766006 cites W3042062301 @default.
- W3096766006 cites W3088058284 @default.
- W3096766006 cites W3102455230 @default.
- W3096766006 cites W4230797216 @default.
- W3096766006 cites W4301523846 @default.
- W3096766006 doi "https://doi.org/10.1101/2020.10.30.362558" @default.
- W3096766006 hasPublicationYear "2020" @default.
- W3096766006 type Work @default.
- W3096766006 sameAs 3096766006 @default.
- W3096766006 citedByCount "4" @default.
- W3096766006 countsByYear W30967660062021 @default.
- W3096766006 countsByYear W30967660062023 @default.
- W3096766006 crossrefType "posted-content" @default.
- W3096766006 hasAuthorship W3096766006A5002759219 @default.
- W3096766006 hasAuthorship W3096766006A5027826197 @default.