Cargando…

nMNSD—A Spiking Neuron-Based Classifier That Combines Weight-Adjustment and Delay-Shift

The recent “multi-neuronal spike sequence detector” (MNSD) architecture integrates the weight- and delay-adjustment methods by combining heterosynaptic plasticity with the neurocomputational feature spike latency, representing a new opportunity to understand the mechanisms underlying biological lear...

Descripción completa

Detalles Bibliográficos
Autores principales: Susi, Gianluca, Antón-Toro, Luis F., Maestú, Fernando, Pereda, Ernesto, Mirasso, Claudio
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7933525/
https://www.ncbi.nlm.nih.gov/pubmed/33679293
http://dx.doi.org/10.3389/fnins.2021.582608
_version_ 1783660630620766208
author Susi, Gianluca
Antón-Toro, Luis F.
Maestú, Fernando
Pereda, Ernesto
Mirasso, Claudio
author_facet Susi, Gianluca
Antón-Toro, Luis F.
Maestú, Fernando
Pereda, Ernesto
Mirasso, Claudio
author_sort Susi, Gianluca
collection PubMed
description The recent “multi-neuronal spike sequence detector” (MNSD) architecture integrates the weight- and delay-adjustment methods by combining heterosynaptic plasticity with the neurocomputational feature spike latency, representing a new opportunity to understand the mechanisms underlying biological learning. Unfortunately, the range of problems to which this topology can be applied is limited because of the low cardinality of the parallel spike trains that it can process, and the lack of a visualization mechanism to understand its internal operation. We present here the nMNSD structure, which is a generalization of the MNSD to any number of inputs. The mathematical framework of the structure is introduced, together with the “trapezoid method,” that is a reduced method to analyze the recognition mechanism operated by the nMNSD in response to a specific input parallel spike train. We apply the nMNSD to a classification problem previously faced with the classical MNSD from the same authors, showing the new possibilities the nMNSD opens, with associated improvement in classification performances. Finally, we benchmark the nMNSD on the classification of static inputs (MNIST database) obtaining state-of-the-art accuracies together with advantageous aspects in terms of time- and energy-efficiency if compared to similar classification methods.
format Online
Article
Text
id pubmed-7933525
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-79335252021-03-06 nMNSD—A Spiking Neuron-Based Classifier That Combines Weight-Adjustment and Delay-Shift Susi, Gianluca Antón-Toro, Luis F. Maestú, Fernando Pereda, Ernesto Mirasso, Claudio Front Neurosci Neuroscience The recent “multi-neuronal spike sequence detector” (MNSD) architecture integrates the weight- and delay-adjustment methods by combining heterosynaptic plasticity with the neurocomputational feature spike latency, representing a new opportunity to understand the mechanisms underlying biological learning. Unfortunately, the range of problems to which this topology can be applied is limited because of the low cardinality of the parallel spike trains that it can process, and the lack of a visualization mechanism to understand its internal operation. We present here the nMNSD structure, which is a generalization of the MNSD to any number of inputs. The mathematical framework of the structure is introduced, together with the “trapezoid method,” that is a reduced method to analyze the recognition mechanism operated by the nMNSD in response to a specific input parallel spike train. We apply the nMNSD to a classification problem previously faced with the classical MNSD from the same authors, showing the new possibilities the nMNSD opens, with associated improvement in classification performances. Finally, we benchmark the nMNSD on the classification of static inputs (MNIST database) obtaining state-of-the-art accuracies together with advantageous aspects in terms of time- and energy-efficiency if compared to similar classification methods. Frontiers Media S.A. 2021-02-19 /pmc/articles/PMC7933525/ /pubmed/33679293 http://dx.doi.org/10.3389/fnins.2021.582608 Text en Copyright © 2021 Susi, Antón-Toro, Maestú, Pereda and Mirasso. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Susi, Gianluca
Antón-Toro, Luis F.
Maestú, Fernando
Pereda, Ernesto
Mirasso, Claudio
nMNSD—A Spiking Neuron-Based Classifier That Combines Weight-Adjustment and Delay-Shift
title nMNSD—A Spiking Neuron-Based Classifier That Combines Weight-Adjustment and Delay-Shift
title_full nMNSD—A Spiking Neuron-Based Classifier That Combines Weight-Adjustment and Delay-Shift
title_fullStr nMNSD—A Spiking Neuron-Based Classifier That Combines Weight-Adjustment and Delay-Shift
title_full_unstemmed nMNSD—A Spiking Neuron-Based Classifier That Combines Weight-Adjustment and Delay-Shift
title_short nMNSD—A Spiking Neuron-Based Classifier That Combines Weight-Adjustment and Delay-Shift
title_sort nmnsd—a spiking neuron-based classifier that combines weight-adjustment and delay-shift
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7933525/
https://www.ncbi.nlm.nih.gov/pubmed/33679293
http://dx.doi.org/10.3389/fnins.2021.582608
work_keys_str_mv AT susigianluca nmnsdaspikingneuronbasedclassifierthatcombinesweightadjustmentanddelayshift
AT antontoroluisf nmnsdaspikingneuronbasedclassifierthatcombinesweightadjustmentanddelayshift
AT maestufernando nmnsdaspikingneuronbasedclassifierthatcombinesweightadjustmentanddelayshift
AT peredaernesto nmnsdaspikingneuronbasedclassifierthatcombinesweightadjustmentanddelayshift
AT mirassoclaudio nmnsdaspikingneuronbasedclassifierthatcombinesweightadjustmentanddelayshift