The covariance perceptron: A new paradigm for classification and processing of time series in recurrent neuronal networks

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Gilson, Matthieu
• dc.contributor.author Dahmen, David
• dc.contributor.author Moreno Bote, Rubén
• dc.contributor.author Insabato, Andrea
• dc.contributor.author Helias, Moritz
• dc.date.accessioned 2021-03-10T08:10:05Z
• dc.date.available 2021-03-10T08:10:05Z
• dc.date.issued 2020
• dc.description.abstract Learning in neuronal networks has developed in many directions, in particular to reproduce cognitive tasks like image recognition and speech processing. Implementations have been inspired by stereotypical neuronal responses like tuning curves in the visual system, where, for example, ON/OFF cells fire or not depending on the contrast in their receptive fields. Classical models of neuronal networks therefore map a set of input signals to a set of activity levels in the output of the network. Each category of inputs is thereby predominantly characterized by its mean. In the case of time series, fluctuations around this mean constitute noise in this view. For this paradigm, the high variability exhibited by the cortical activity may thus imply limitations or constraints, which have been discussed for many years. For example, the need for averaging neuronal activity over long periods or large groups of cells to assess a robust mean and to diminish the effect of noise correlations. To reconcile robust computations with variable neuronal activity, we here propose a conceptual change of perspective by employing variability of activity as the basis for stimulus-related information to be learned by neurons, rather than merely being the noise that corrupts the mean signal. In this new paradigm both afferent and recurrent weights in a network are tuned to shape the input-output mapping for covariances, the second-order statistics of the fluctuating activity. When including time lags, covariance patterns define a natural metric for time series that capture their propagating nature. We develop the theory for classification of time series based on their spatio-temporal covariances, which reflect dynamical properties. We demonstrate that recurrent connectivity is able to transform information contained in the temporal structure of the signal into spatial covariances. Finally, we use the MNIST database to show how the covariance perceptron can capture specific second-order statistical patterns generated by moving digits.
• dc.description.sponsorship This work was partially supported by the European Union’s Horizon 2020 research and innovation programme under grant agreement No.785907 (Human Brain Project SGA2). MG acknowledges funding from the Marie Sklodowska-Curie Action (Grant H2020-MSCA656547) of the European Commission. DD and MH acknowledge the Helmholtz young investigator’s group (VH-NG-1028), the Exploratory Research Space (ERS) seed fund neuroIC002 (EXS-SFneuroIC002) of the RWTH university and the JARA Center for Doctoral studies within the graduate School for Simulation and Data Science (SSD). AI acknowledges funding from the Marie Sklodowska-Curie Action (Grant H2020-MSCA841684) of the European Commission. RMB acknowledges funding from the Howard Hughes Medical Institute (HHMI, ref 55008742), MINECO (Spain; BFU2017-85936-P) and ICREA Academia (2016). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript
• dc.format.mimetype application/pdf
• dc.identifier.citation Gilson M, Dahmen D, Moreno-Bote R, Insabato A, Helias M. The covariance perceptron: A new paradigm for classification and processing of time series in recurrent neuronal networks. PLoS Comput Biol. 2020 Oct 12;16(10):e1008127. DOI: 10.1371/journal.pcbi.1008127
• dc.identifier.doi http://dx.doi.org/10.1371/journal.pcbi.1008127
• dc.identifier.issn 1544-9173
• dc.identifier.uri http://hdl.handle.net/10230/46715
• dc.language.iso eng
• dc.publisher Public Library of Science (PLoS)
• dc.relation.ispartof PLoS Comput Biol. 2020 Oct 12;16(10):e1008127
• dc.relation.projectID info:eu-repo/grantAgreement/ES/2PE/BFU2017-85936-P
• dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/785907
• dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/656547
• dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/841684
• dc.rights © 2020 Gilson et al. This is an open access article distributed under the terms of the Creative Commons Attribution License https://creativecommons.org/licenses/by/4.0/, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.rights.uri https://creativecommons.org/licenses/by/4.0/
• dc.subject.keyword Computational Biology
• dc.subject.keyword Computer Simulation
• dc.subject.keyword Image Processing
• dc.subject.keyword Neural Networks
• dc.title The covariance perceptron: A new paradigm for classification and processing of time series in recurrent neuronal networks
• dc.type info:eu-repo/semantics/article
• dc.type.version info:eu-repo/semantics/publishedVersion