Cargando…

Event-Based Trajectory Prediction Using Spiking Neural Networks

In recent years, event-based sensors have been combined with spiking neural networks (SNNs) to create a new generation of bio-inspired artificial vision systems. These systems can process spatio-temporal data in real time, and are highly energy efficient. In this study, we used a new hybrid event-ba...

Descripción completa

Detalles Bibliográficos
Autores principales: Debat, Guillaume, Chauhan, Tushar, Cottereau, Benoit R., Masquelier, Timothée, Paindavoine, Michel, Baures, Robin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8180888/
https://www.ncbi.nlm.nih.gov/pubmed/34108870
http://dx.doi.org/10.3389/fncom.2021.658764
_version_ 1783704043853447168
author Debat, Guillaume
Chauhan, Tushar
Cottereau, Benoit R.
Masquelier, Timothée
Paindavoine, Michel
Baures, Robin
author_facet Debat, Guillaume
Chauhan, Tushar
Cottereau, Benoit R.
Masquelier, Timothée
Paindavoine, Michel
Baures, Robin
author_sort Debat, Guillaume
collection PubMed
description In recent years, event-based sensors have been combined with spiking neural networks (SNNs) to create a new generation of bio-inspired artificial vision systems. These systems can process spatio-temporal data in real time, and are highly energy efficient. In this study, we used a new hybrid event-based camera in conjunction with a multi-layer spiking neural network trained with a spike-timing-dependent plasticity learning rule. We showed that neurons learn from repeated and correlated spatio-temporal patterns in an unsupervised way and become selective to motion features, such as direction and speed. This motion selectivity can then be used to predict ball trajectory by adding a simple read-out layer composed of polynomial regressions, and trained in a supervised manner. Hence, we show that a SNN receiving inputs from an event-based sensor can extract relevant spatio-temporal patterns to process and predict ball trajectories.
format Online
Article
Text
id pubmed-8180888
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-81808882021-06-08 Event-Based Trajectory Prediction Using Spiking Neural Networks Debat, Guillaume Chauhan, Tushar Cottereau, Benoit R. Masquelier, Timothée Paindavoine, Michel Baures, Robin Front Comput Neurosci Neuroscience In recent years, event-based sensors have been combined with spiking neural networks (SNNs) to create a new generation of bio-inspired artificial vision systems. These systems can process spatio-temporal data in real time, and are highly energy efficient. In this study, we used a new hybrid event-based camera in conjunction with a multi-layer spiking neural network trained with a spike-timing-dependent plasticity learning rule. We showed that neurons learn from repeated and correlated spatio-temporal patterns in an unsupervised way and become selective to motion features, such as direction and speed. This motion selectivity can then be used to predict ball trajectory by adding a simple read-out layer composed of polynomial regressions, and trained in a supervised manner. Hence, we show that a SNN receiving inputs from an event-based sensor can extract relevant spatio-temporal patterns to process and predict ball trajectories. Frontiers Media S.A. 2021-05-24 /pmc/articles/PMC8180888/ /pubmed/34108870 http://dx.doi.org/10.3389/fncom.2021.658764 Text en Copyright © 2021 Debat, Chauhan, Cottereau, Masquelier, Paindavoine and Baures. https://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
Debat, Guillaume
Chauhan, Tushar
Cottereau, Benoit R.
Masquelier, Timothée
Paindavoine, Michel
Baures, Robin
Event-Based Trajectory Prediction Using Spiking Neural Networks
title Event-Based Trajectory Prediction Using Spiking Neural Networks
title_full Event-Based Trajectory Prediction Using Spiking Neural Networks
title_fullStr Event-Based Trajectory Prediction Using Spiking Neural Networks
title_full_unstemmed Event-Based Trajectory Prediction Using Spiking Neural Networks
title_short Event-Based Trajectory Prediction Using Spiking Neural Networks
title_sort event-based trajectory prediction using spiking neural networks
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8180888/
https://www.ncbi.nlm.nih.gov/pubmed/34108870
http://dx.doi.org/10.3389/fncom.2021.658764
work_keys_str_mv AT debatguillaume eventbasedtrajectorypredictionusingspikingneuralnetworks
AT chauhantushar eventbasedtrajectorypredictionusingspikingneuralnetworks
AT cottereaubenoitr eventbasedtrajectorypredictionusingspikingneuralnetworks
AT masqueliertimothee eventbasedtrajectorypredictionusingspikingneuralnetworks
AT paindavoinemichel eventbasedtrajectorypredictionusingspikingneuralnetworks
AT bauresrobin eventbasedtrajectorypredictionusingspikingneuralnetworks