Spatial Concept Learning: A Spiking Neural Network Implementation in Virtual and Physical Robots

Spatial Concept Learning: A Spiking Neural Network Implementation in Virtual and Physical Robots

This paper proposes an artificial spiking neural network (SNN) sustaining the cognitive abstract process of spatial concept learning, embedded in virtual and real robots. Based on an operant conditioning procedure, the robots learn the relationship of horizontal/vertical and left/right visual stimul...

Full description

Bibliographic Details
Main Authors: André Cyr, Frédéric Thériault
Format: Article
Language:English
Published: Hindawi Limited 2019-01-01
Series:Computational Intelligence and Neuroscience
Online Access:http://dx.doi.org/10.1155/2019/8361369
id doaj-99d8592784aa4bcc9e7be0790b529afc
record_format Article
spelling doaj-99d8592784aa4bcc9e7be0790b529afc2020-11-25T00:30:56ZengHindawi LimitedComputational Intelligence and Neuroscience1687-52651687-52732019-01-01201910.1155/2019/83613698361369Spatial Concept Learning: A Spiking Neural Network Implementation in Virtual and Physical RobotsAndré Cyr0Frédéric Thériault1School of Psychology, University of Ottawa, Ottawa, Ontario, CanadaDepartment of Computer Science, Cégep du Vieux Montréal, Montréal, Quebec, CanadaThis paper proposes an artificial spiking neural network (SNN) sustaining the cognitive abstract process of spatial concept learning, embedded in virtual and real robots. Based on an operant conditioning procedure, the robots learn the relationship of horizontal/vertical and left/right visual stimuli, regardless of their specific pattern composition or their location on the images. Tests with novel patterns and locations were successfully completed after the acquisition learning phase. Results show that the SNN can adapt its behavior in real time when the rewarding rule changes.http://dx.doi.org/10.1155/2019/8361369
collection DOAJ
language English
format Article
sources DOAJ
author André Cyr
Frédéric Thériault
spellingShingle André Cyr
Frédéric Thériault
Spatial Concept Learning: A Spiking Neural Network Implementation in Virtual and Physical Robots
Computational Intelligence and Neuroscience
author_facet André Cyr
Frédéric Thériault
author_sort André Cyr
title Spatial Concept Learning: A Spiking Neural Network Implementation in Virtual and Physical Robots
title_short Spatial Concept Learning: A Spiking Neural Network Implementation in Virtual and Physical Robots
title_full Spatial Concept Learning: A Spiking Neural Network Implementation in Virtual and Physical Robots
title_fullStr Spatial Concept Learning: A Spiking Neural Network Implementation in Virtual and Physical Robots
title_full_unstemmed Spatial Concept Learning: A Spiking Neural Network Implementation in Virtual and Physical Robots
title_sort spatial concept learning: a spiking neural network implementation in virtual and physical robots
publisher Hindawi Limited
series Computational Intelligence and Neuroscience
issn 1687-5265
1687-5273
publishDate 2019-01-01
description This paper proposes an artificial spiking neural network (SNN) sustaining the cognitive abstract process of spatial concept learning, embedded in virtual and real robots. Based on an operant conditioning procedure, the robots learn the relationship of horizontal/vertical and left/right visual stimuli, regardless of their specific pattern composition or their location on the images. Tests with novel patterns and locations were successfully completed after the acquisition learning phase. Results show that the SNN can adapt its behavior in real time when the rewarding rule changes.
url http://dx.doi.org/10.1155/2019/8361369
work_keys_str_mv AT andrecyr spatialconceptlearningaspikingneuralnetworkimplementationinvirtualandphysicalrobots
AT frederictheriault spatialconceptlearningaspikingneuralnetworkimplementationinvirtualandphysicalrobots
_version_ 1725324902006784000

Similar Items