Machine Learning for Neural Decoding.
Deep learning
Hippocampus
Machine learning
Motor cortex
Neural data analysis
Neural decoding
Somatosensory cortex
Journal
eNeuro
ISSN: 2373-2822
Titre abrégé: eNeuro
Pays: United States
ID NLM: 101647362
Informations de publication
Date de publication:
Historique:
received:
04
12
2019
revised:
01
07
2020
accepted:
03
07
2020
pubmed:
2
8
2020
medline:
22
6
2021
entrez:
2
8
2020
Statut:
epublish
Résumé
Despite rapid advances in machine learning tools, the majority of neural decoding approaches still use traditional methods. Modern machine learning tools, which are versatile and easy to use, have the potential to significantly improve decoding performance. This tutorial describes how to effectively apply these algorithms for typical decoding problems. We provide descriptions, best practices, and code for applying common machine learning methods, including neural networks and gradient boosting. We also provide detailed comparisons of the performance of various methods at the task of decoding spiking activity in motor cortex, somatosensory cortex, and hippocampus. Modern methods, particularly neural networks and ensembles, significantly outperform traditional approaches, such as Wiener and Kalman filters. Improving the performance of neural decoding algorithms allows neuroscientists to better understand the information contained in a neural population and can help to advance engineering applications such as brain-machine interfaces. Our code package is available at github.com/kordinglab/neural_decoding.
Identifiants
pubmed: 32737181
pii: ENEURO.0506-19.2020
doi: 10.1523/ENEURO.0506-19.2020
pmc: PMC7470933
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
Copyright © 2020 Glaser et al.
Références
Neuroimage. 2012 Apr 2;60(2):1186-93
pubmed: 22281674
J Neurophysiol. 1998 Feb;79(2):1017-44
pubmed: 9463459
Prog Neurobiol. 2019 Apr;175:126-137
pubmed: 30738835
J Neurophysiol. 2019 Jan 1;121(1):61-73
pubmed: 30379603
IEEE Trans Neural Syst Rehabil Eng. 2005 Jun;13(2):131-6
pubmed: 16003890
Science. 2005 Nov 4;310(5749):863-6
pubmed: 16272124
Front Neurorobot. 2013 Dec 04;7:21
pubmed: 24409142
Nature. 2012 May 17;485(7398):368-71
pubmed: 22522928
J Neural Eng. 2012 Apr;9(2):026027
pubmed: 22427488
IEEE Trans Neural Syst Rehabil Eng. 2008 Jun;16(3):213-22
pubmed: 18586600
Nat Neurosci. 2016 Jul;19(7):973-80
pubmed: 27273768
J Neurosci. 2006 Mar 29;26(13):3615-20
pubmed: 16571770
Sensors (Basel). 2012;12(2):1211-79
pubmed: 22438708
Nature. 2015 May 28;521(7553):436-44
pubmed: 26017442
Nat Commun. 2016 Dec 13;7:13749
pubmed: 27958268
Neuron. 2020 Apr 22;106(2):316-328.e6
pubmed: 32105611
J Neurophysiol. 2014 Jan;111(1):217-27
pubmed: 24089403
Lancet. 2013 Feb 16;381(9866):557-64
pubmed: 23253623
PLoS Biol. 2003 Nov;1(2):E42
pubmed: 14624244
Nat Neurosci. 2014 Dec;17(12):1784-1792
pubmed: 25383902
Nature. 2016 Jan 28;529(7587):484-9
pubmed: 26819042
Nat Neurosci. 2012 Dec;15(12):1752-7
pubmed: 23160043
Nat Commun. 2018 May 3;9(1):1788
pubmed: 29725023
Neuron. 2010 Apr 29;66(2):300-14
pubmed: 20435005
Neuron. 2003 Sep 25;40(1):177-88
pubmed: 14527442
Neural Comput. 1997 Nov 15;9(8):1735-80
pubmed: 9377276
Neural Comput. 2016 Nov;28(11):2291-2319
pubmed: 27626960
Elife. 2017 Apr 24;6:
pubmed: 28418332
J Neural Eng. 2007 Dec;4(4):369-79
pubmed: 18057504
Neuron. 2010 Jul 15;67(1):25-32
pubmed: 20624589
Elife. 2016 Jul 15;5:
pubmed: 27420609
IEEE Trans Neural Syst Rehabil Eng. 2009 Oct;17(5):487-96
pubmed: 19666343
Neuron. 2009 Aug 27;63(4):497-507
pubmed: 19709631
Biol Cybern. 2003 Mar;88(3):219-28
pubmed: 12647229
Nature. 2002 Mar 14;416(6877):141-2
pubmed: 11894084
Neuron. 2009 Oct 29;64(2):267-80
pubmed: 19874793
Curr Opin Neurobiol. 2019 Apr;55:167-179
pubmed: 31039527
IEEE Trans Biomed Eng. 2017 Apr;64(4):935-945
pubmed: 27337709
Front Comput Neurosci. 2018 Jul 19;12:56
pubmed: 30072887
Neuroimage. 2015 Apr 15;110:48-59
pubmed: 25623501