Rapid adaptation of brain-computer interfaces to new neuronal ensembles or participants via generative modelling.
Journal
Nature biomedical engineering
ISSN: 2157-846X
Titre abrégé: Nat Biomed Eng
Pays: England
ID NLM: 101696896
Informations de publication
Date de publication:
04 2023
04 2023
Historique:
received:
13
06
2020
accepted:
17
09
2021
medline:
28
4
2023
pubmed:
20
11
2021
entrez:
19
11
2021
Statut:
ppublish
Résumé
For brain-computer interfaces (BCIs), obtaining sufficient training data for algorithms that map neural signals onto actions can be difficult, expensive or even impossible. Here we report the development and use of a generative model-a model that synthesizes a virtually unlimited number of new data distributions from a learned data distribution-that learns mappings between hand kinematics and the associated neural spike trains. The generative spike-train synthesizer is trained on data from one recording session with a monkey performing a reaching task and can be rapidly adapted to new sessions or monkeys by using limited additional neural data. We show that the model can be adapted to synthesize new spike trains, accelerating the training and improving the generalization of BCI decoders. The approach is fully data-driven, and hence, applicable to applications of BCIs beyond motor control.
Identifiants
pubmed: 34795394
doi: 10.1038/s41551-021-00811-z
pii: 10.1038/s41551-021-00811-z
pmc: PMC9114171
mid: NIHMS1741424
doi:
Types de publication
Journal Article
Research Support, U.S. Gov't, Non-P.H.S.
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
546-558Subventions
Organisme : NINDS NIH HHS
ID : F31 NS092356
Pays : United States
Organisme : NINDS NIH HHS
ID : R01 NS053603
Pays : United States
Organisme : NINDS NIH HHS
ID : R01 NS074044
Pays : United States
Informations de copyright
© 2021. The Author(s), under exclusive licence to Springer Nature Limited.
Références
Front Neurosci. 2011 May 11;5:68
pubmed: 21617732
Neural Comput. 2013 Feb;25(2):328-73
pubmed: 23148415
PLoS Biol. 2003 Nov;1(2):E42
pubmed: 14624244
J Neural Eng. 2014 Dec;11(6):066003
pubmed: 25307561
Nature. 2004 Oct 14;431(7010):768-74
pubmed: 15483597
Neural Comput. 1997 Nov 15;9(8):1735-80
pubmed: 9377276
Nat Biomed Eng. 2017 Dec;1(12):967-976
pubmed: 31015712
Nat Neurosci. 2018 Apr;21(4):607-616
pubmed: 29531364
Nature. 2000 Nov 16;408(6810):361-5
pubmed: 11099043
Annu Rev Neurosci. 2007;30:535-74
pubmed: 17600525
Nature. 2000 Oct 12;407(6805):742-7
pubmed: 11048720
Neuron. 2017 Feb 22;93(4):955-970.e5
pubmed: 28190641
Nat Neurosci. 2018 Dec;21(12):1774-1783
pubmed: 30482949
Nat Neurosci. 2020 Feb;23(2):260-270
pubmed: 31907438
Nat Commun. 2017 Mar 20;8:14787
pubmed: 28317912
eNeuro. 2020 Aug 31;7(4):
pubmed: 32737181
Nat Commun. 2016 Dec 13;7:13749
pubmed: 27958268
J Neurosci. 2004 Sep 29;24(39):8551-61
pubmed: 15456829
Neural Comput. 2004 May;16(5):971-98
pubmed: 15070506
Nature. 2014 Aug 28;512(7515):423-6
pubmed: 25164754
PLoS One. 2009 Jul 15;4(7):e6243
pubmed: 19603074
Nat Methods. 2018 Oct;15(10):805-815
pubmed: 30224673
Nature. 2008 Jun 19;453(7198):1098-101
pubmed: 18509337
Science. 2002 Jun 7;296(5574):1829-32
pubmed: 12052948
Nat Neurosci. 2005 Dec;8(12):1643-6
pubmed: 16306891
Curr Opin Neurobiol. 2008 Dec;18(6):589-94
pubmed: 18838120
ACS Chem Neurosci. 2015 Jan 21;6(1):48-67
pubmed: 25546652
Nat Biomed Eng. 2020 Jul;4(7):672-685
pubmed: 32313100
Prog Brain Res. 2007;165:493-507
pubmed: 17925266
J Neurophysiol. 2004 Apr;91(4):1899-907
pubmed: 15010499