AbstractRapid 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 often depends on manual operations and requires considerable knowledge about the nature of the representation. 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 behavioural variables directly from wide-band neural data. The network requires little user input and generalizes across stimuli, behaviours, brain regions, and recording techniques. Once trained, it can be analysed to determine elements of the neural code that are informative about a given variable. We validated this approach using data from rodent auditory cortex and hippocampus, identifying a novel representation of head direction encoded by putative CA1 interneurons.
%0 Unpublished Work
%1 Frey2019-wd
%A Frey, Markus
%A Tanni, Sander
%A Perrodin, Catherine
%A O'Leary, Alice
%A Nau, Matthias
%A Kelly, Jack
%A Banino, Andrea
%A Bendor, Daniel
%A Doeller, Christian F
%A Barry, Caswell
%D 2019
%J bioRxiv
%K
%T Interpreting wide-band neural activity using convolutional neural networks
%X AbstractRapid 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 often depends on manual operations and requires considerable knowledge about the nature of the representation. 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 behavioural variables directly from wide-band neural data. The network requires little user input and generalizes across stimuli, behaviours, brain regions, and recording techniques. Once trained, it can be analysed to determine elements of the neural code that are informative about a given variable. We validated this approach using data from rodent auditory cortex and hippocampus, identifying a novel representation of head direction encoded by putative CA1 interneurons.
@unpublished{Frey2019-wd,
abstract = {AbstractRapid 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 often depends on manual operations and requires considerable knowledge about the nature of the representation. 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 behavioural variables directly from wide-band neural data. The network requires little user input and generalizes across stimuli, behaviours, brain regions, and recording techniques. Once trained, it can be analysed to determine elements of the neural code that are informative about a given variable. We validated this approach using data from rodent auditory cortex and hippocampus, identifying a novel representation of head direction encoded by putative CA1 interneurons.},
added-at = {2024-09-10T11:56:37.000+0200},
author = {Frey, Markus and Tanni, Sander and Perrodin, Catherine and O'Leary, Alice and Nau, Matthias and Kelly, Jack and Banino, Andrea and Bendor, Daniel and Doeller, Christian F and Barry, Caswell},
biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/22c6529862ddb80876bb9a3b09764b80e/scadsfct},
institution = {bioRxiv},
interhash = {f4a629057931d7977c0bb57d0790e7c9},
intrahash = {2c6529862ddb80876bb9a3b09764b80e},
journal = {bioRxiv},
keywords = {},
month = dec,
timestamp = {2024-09-10T15:15:57.000+0200},
title = {Interpreting wide-band neural activity using convolutional neural networks},
year = 2019
}
