MOTION LEARNING USING SPATIO-TEMPORAL NEURAL NETWORK

Motion trajectory prediction is one of the key areas in behaviour and surveillance studies. Many related successful applications have been reported in the literature. However, most of the studiesare based on sigmoidal neural networks in which some dynamic properties of the data are overlooked due to...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Nooraini Yusoff, Farzana Kabir-Ahmad, Mohamad-Farif Jemili
Formato:	article
Lenguaje:	EN
Publicado:	UUM Press 2020
Materias:	motion learning reinforcement learning reward-modulated spike-timing-dependent plasticity spatio-temporal neural network Information technology T58.5-58.64
Acceso en línea:	https://doaj.org/article/0318b47f190348ffaddea490a5dfe265
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0318b47f190348ffaddea490a5dfe265
record_format	dspace
spelling	oai:doaj.org-article:0318b47f190348ffaddea490a5dfe2652021-11-11T03:36:45ZMOTION LEARNING USING SPATIO-TEMPORAL NEURAL NETWORK10.32890/jict2020.19.2.31675-414X2180-3862https://doaj.org/article/0318b47f190348ffaddea490a5dfe2652020-03-01T00:00:00Zhttp://e-journal.uum.edu.my/index.php/jict/article/view/jict2020.19.2.3https://doaj.org/toc/1675-414Xhttps://doaj.org/toc/2180-3862Motion trajectory prediction is one of the key areas in behaviour and surveillance studies. Many related successful applications have been reported in the literature. However, most of the studiesare based on sigmoidal neural networks in which some dynamic properties of the data are overlooked due to the absence of spatiotemporal encoding functionalities. Even though some sequential (motion) learning studies have been proposed using spatiotemporal neural networks, as in those sigmoidal neural networks, the approach used is mainly supervised learning. In such learning, it requires a target signal, in which this is not always available in some applications. For this study, motion learning using spatiotemporal neural network is proposed. The learning is based onreward-modulated spike-timing-dependent plasticity (STDP), whereby the learning weight adjustment provided by the standard STDP is modulated by the reinforcement. The implementationof reinforcement approach for motion trajectory can be regarded as a major contribution of this study. In this study, learning is implemented on a reward basis without the need for learningtargets. The algorithm has shown good potential in learning motion trajectory particularly in noisy and dynamic settings. Furthermore, the learning uses generic neural network architecture, whichmakes learning adaptable for many applications. Nooraini YusoffFarzana Kabir-AhmadMohamad-Farif JemiliUUM Pressarticlemotion learningreinforcement learningreward-modulated spike-timing-dependent plasticityspatio-temporal neural networkInformation technologyT58.5-58.64ENJournal of ICT, Vol 19, Iss 2 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	motion learning reinforcement learning reward-modulated spike-timing-dependent plasticity spatio-temporal neural network Information technology T58.5-58.64
spellingShingle	motion learning reinforcement learning reward-modulated spike-timing-dependent plasticity spatio-temporal neural network Information technology T58.5-58.64 Nooraini Yusoff Farzana Kabir-Ahmad Mohamad-Farif Jemili MOTION LEARNING USING SPATIO-TEMPORAL NEURAL NETWORK
description	Motion trajectory prediction is one of the key areas in behaviour and surveillance studies. Many related successful applications have been reported in the literature. However, most of the studiesare based on sigmoidal neural networks in which some dynamic properties of the data are overlooked due to the absence of spatiotemporal encoding functionalities. Even though some sequential (motion) learning studies have been proposed using spatiotemporal neural networks, as in those sigmoidal neural networks, the approach used is mainly supervised learning. In such learning, it requires a target signal, in which this is not always available in some applications. For this study, motion learning using spatiotemporal neural network is proposed. The learning is based onreward-modulated spike-timing-dependent plasticity (STDP), whereby the learning weight adjustment provided by the standard STDP is modulated by the reinforcement. The implementationof reinforcement approach for motion trajectory can be regarded as a major contribution of this study. In this study, learning is implemented on a reward basis without the need for learningtargets. The algorithm has shown good potential in learning motion trajectory particularly in noisy and dynamic settings. Furthermore, the learning uses generic neural network architecture, whichmakes learning adaptable for many applications.
format	article
author	Nooraini Yusoff Farzana Kabir-Ahmad Mohamad-Farif Jemili
author_facet	Nooraini Yusoff Farzana Kabir-Ahmad Mohamad-Farif Jemili
author_sort	Nooraini Yusoff
title	MOTION LEARNING USING SPATIO-TEMPORAL NEURAL NETWORK
title_short	MOTION LEARNING USING SPATIO-TEMPORAL NEURAL NETWORK
title_full	MOTION LEARNING USING SPATIO-TEMPORAL NEURAL NETWORK
title_fullStr	MOTION LEARNING USING SPATIO-TEMPORAL NEURAL NETWORK
title_full_unstemmed	MOTION LEARNING USING SPATIO-TEMPORAL NEURAL NETWORK
title_sort	motion learning using spatio-temporal neural network
publisher	UUM Press
publishDate	2020
url	https://doaj.org/article/0318b47f190348ffaddea490a5dfe265
work_keys_str_mv	AT noorainiyusoff motionlearningusingspatiotemporalneuralnetwork AT farzanakabirahmad motionlearningusingspatiotemporalneuralnetwork AT mohamadfarifjemili motionlearningusingspatiotemporalneuralnetwork
_version_	1718439556438556672

MOTION LEARNING USING SPATIO-TEMPORAL NEURAL NETWORK

Ejemplares similares