Cargando…

Interpreting wide-band neural activity using convolutional neural networks

Rapid progress in technologies such as calcium imaging and electrophysiology has seen a dramatic increase in the size and extent of neural recordings. Even so, interpretation of this data requires considerable knowledge about the nature of the representation and often depends on manual operations. D...

Descripción completa

Detalles Bibliográficos
Autores principales: Frey, Markus, Tanni, Sander, Perrodin, Catherine, O'Leary, Alice, Nau, Matthias, Kelly, Jack, Banino, Andrea, Bendor, Daniel, Lefort, Julie, Doeller, Christian F, Barry, Caswell
Formato: Online Artículo Texto
Lenguaje:English
Publicado: eLife Sciences Publications, Ltd 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8328518/
https://www.ncbi.nlm.nih.gov/pubmed/34338632
http://dx.doi.org/10.7554/eLife.66551
_version_ 1783732334175977472
author Frey, Markus
Tanni, Sander
Perrodin, Catherine
O'Leary, Alice
Nau, Matthias
Kelly, Jack
Banino, Andrea
Bendor, Daniel
Lefort, Julie
Doeller, Christian F
Barry, Caswell
author_facet Frey, Markus
Tanni, Sander
Perrodin, Catherine
O'Leary, Alice
Nau, Matthias
Kelly, Jack
Banino, Andrea
Bendor, Daniel
Lefort, Julie
Doeller, Christian F
Barry, Caswell
author_sort Frey, Markus
collection PubMed
description Rapid progress in technologies such as calcium imaging and electrophysiology has seen a dramatic increase in the size and extent of neural recordings. Even so, interpretation of this data requires considerable knowledge about the nature of the representation and often depends on manual operations. Decoding provides a means to infer the information content of such recordings but typically requires highly processed data and prior knowledge of the encoding scheme. Here, we developed a deep-learning framework able to decode sensory and behavioral variables directly from wide-band neural data. The network requires little user input and generalizes across stimuli, behaviors, brain regions, and recording techniques. Once trained, it can be analyzed to determine elements of the neural code that are informative about a given variable. We validated this approach using electrophysiological and calcium-imaging data from rodent auditory cortex and hippocampus as well as human electrocorticography (ECoG) data. We show successful decoding of finger movement, auditory stimuli, and spatial behaviors – including a novel representation of head direction - from raw neural activity.
format Online
Article
Text
id pubmed-8328518
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher eLife Sciences Publications, Ltd
record_format MEDLINE/PubMed
spelling pubmed-83285182021-08-04 Interpreting wide-band neural activity using convolutional neural networks Frey, Markus Tanni, Sander Perrodin, Catherine O'Leary, Alice Nau, Matthias Kelly, Jack Banino, Andrea Bendor, Daniel Lefort, Julie Doeller, Christian F Barry, Caswell eLife Neuroscience Rapid progress in technologies such as calcium imaging and electrophysiology has seen a dramatic increase in the size and extent of neural recordings. Even so, interpretation of this data requires considerable knowledge about the nature of the representation and often depends on manual operations. Decoding provides a means to infer the information content of such recordings but typically requires highly processed data and prior knowledge of the encoding scheme. Here, we developed a deep-learning framework able to decode sensory and behavioral variables directly from wide-band neural data. The network requires little user input and generalizes across stimuli, behaviors, brain regions, and recording techniques. Once trained, it can be analyzed to determine elements of the neural code that are informative about a given variable. We validated this approach using electrophysiological and calcium-imaging data from rodent auditory cortex and hippocampus as well as human electrocorticography (ECoG) data. We show successful decoding of finger movement, auditory stimuli, and spatial behaviors – including a novel representation of head direction - from raw neural activity. eLife Sciences Publications, Ltd 2021-08-02 /pmc/articles/PMC8328518/ /pubmed/34338632 http://dx.doi.org/10.7554/eLife.66551 Text en © 2021, Frey et al https://creativecommons.org/licenses/by/4.0/This article is distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use and redistribution provided that the original author and source are credited.
spellingShingle Neuroscience
Frey, Markus
Tanni, Sander
Perrodin, Catherine
O'Leary, Alice
Nau, Matthias
Kelly, Jack
Banino, Andrea
Bendor, Daniel
Lefort, Julie
Doeller, Christian F
Barry, Caswell
Interpreting wide-band neural activity using convolutional neural networks
title Interpreting wide-band neural activity using convolutional neural networks
title_full Interpreting wide-band neural activity using convolutional neural networks
title_fullStr Interpreting wide-band neural activity using convolutional neural networks
title_full_unstemmed Interpreting wide-band neural activity using convolutional neural networks
title_short Interpreting wide-band neural activity using convolutional neural networks
title_sort interpreting wide-band neural activity using convolutional neural networks
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8328518/
https://www.ncbi.nlm.nih.gov/pubmed/34338632
http://dx.doi.org/10.7554/eLife.66551
work_keys_str_mv AT freymarkus interpretingwidebandneuralactivityusingconvolutionalneuralnetworks
AT tannisander interpretingwidebandneuralactivityusingconvolutionalneuralnetworks
AT perrodincatherine interpretingwidebandneuralactivityusingconvolutionalneuralnetworks
AT olearyalice interpretingwidebandneuralactivityusingconvolutionalneuralnetworks
AT naumatthias interpretingwidebandneuralactivityusingconvolutionalneuralnetworks
AT kellyjack interpretingwidebandneuralactivityusingconvolutionalneuralnetworks
AT baninoandrea interpretingwidebandneuralactivityusingconvolutionalneuralnetworks
AT bendordaniel interpretingwidebandneuralactivityusingconvolutionalneuralnetworks
AT lefortjulie interpretingwidebandneuralactivityusingconvolutionalneuralnetworks
AT doellerchristianf interpretingwidebandneuralactivityusingconvolutionalneuralnetworks
AT barrycaswell interpretingwidebandneuralactivityusingconvolutionalneuralnetworks