English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Interpreting wide-band neural activity using convolutional neural networks

Frey, M., Tanni, S., Perrodin, C., O'Leary, A., Nau, M., Kelly, J., et al. (2021). Interpreting wide-band neural activity using convolutional neural networks. eLife, 10: e66551. doi:10.7554/eLife.66551.

Item is

Basic

show hide
Genre: Journal Article

Files

show Files
hide Files
:
Frey_2021.pdf (Publisher version), 3MB
Name:
Frey_2021.pdf
Description:
-
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Frey, Markus1, 2, Author
Tanni, Sander3, Author
Perrodin, Catherine4, Author
O'Leary, Alice3, Author
Nau, Matthias1, 2, Author              
Kelly, Jack5, Author
Banino, Andrea6, Author
Bendor, Daniel4, Author
Lefort, Julie3, Author
Doeller, Christian F.1, 2, 7, Author              
Barry, Caswell3, Author
Affiliations:
1Egil and Pauline Braathen and Fred Kavli Centre for Cortical Microcircuits, Kavli Institute, Norwegian University of Science and Technology, Trondheim, Norway, ou_persistent22              
2Department Psychology (Doeller), MPI for Human Cognitive and Brain Sciences, Max Planck Society, Leipzig, DE, ou_2591710              
3Department of Cell and Developmental Biology, University College London, United Kingdom, ou_persistent22              
4Institute of Behavioural Neuroscience, University College London, United Kingdom, ou_persistent22              
5Open Climate Fix, London, United Kingdom, ou_persistent22              
6DeepMind, London, United Kingdom, ou_persistent22              
7Institute of Psychology, University of Leipzig, Germany, ou_persistent22              

Content

show
hide
Free keywords: Calcium imaging; Decoding; Deep learning; Electrophysiology; Neuroscience; Rat
 Abstract: 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.

Details

show
hide
Language(s): eng - English
 Dates: 2021-01-152021-07-132021-08-02
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.7554/eLife.66551
PMID: 34338632
PMC: PMC8328518
 Degree: -

Event

show

Legal Case

show

Project information

show hide
Project name : -
Grant ID : ERC-CoG GEOCOG 724836
Funding program : Horizon 2020
Funding organization : European Research Council
Project name : -
Grant ID : 212281/Z/18/Z and 110238/Z/15/Z
Funding program : -
Funding organization : Wellcome Trust

Source 1

show
hide
Title: eLife
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 10 Sequence Number: e66551 Start / End Page: - Identifier: ISSN: 2050-084X
CoNE: https://pure.mpg.de/cone/journals/resource/2050-084X