Two Novel Learning Algorithms for CMAC Neural Network Based on Changeable Learning Rate

Cerebellar Model Articulation Controller Neural Network is a computational model of cerebellum which acts as a lookup table. The advantages of CMAC are fast learning convergence, and capability of mapping nonlinear functions due to its local generalization of weight updating, single structure and ea...

Full description

Bibliographic Details
Main Authors:	Nazal Modhej, Mohammad Teshnehlab, Mashallah Abbasi Dezfouli
Format:	Article
Language:	English
Published:	Science and Research Branch,Islamic Azad University 2015-02-01
Series:	Journal of Advances in Computer Engineering and Technology
Subjects:	cmac learning rate training iteration learning performance
Online Access:	https://jacet.srbiau.ac.ir/article_6107_aaa4c27e8f25242fed342b4f25718026.pdf

id	doaj-205910417b7a477a904c1c7ff17df15b
record_format	Article
spelling	doaj-205910417b7a477a904c1c7ff17df15b2021-10-11T09:52:29ZengScience and Research Branch,Islamic Azad UniversityJournal of Advances in Computer Engineering and Technology2423-41922423-42062015-02-011137426107Two Novel Learning Algorithms for CMAC Neural Network Based on Changeable Learning RateNazal Modhej0Mohammad Teshnehlab1Mashallah Abbasi Dezfouli2Department of Computer Engineering, Science and Research Branch, Islamic Azad University, Khouzestan.Khaje Nasir Toosi University of TechnologyDepartment of Computer Engineering, Science and Research Branch, Islamic Azad University, KhouzestanCerebellar Model Articulation Controller Neural Network is a computational model of cerebellum which acts as a lookup table. The advantages of CMAC are fast learning convergence, and capability of mapping nonlinear functions due to its local generalization of weight updating, single structure and easy processing. In the training phase, the disadvantage of some CMAC models is unstable phenomenon or slower convergence speed due to larger fixed or smaller fixed learning rate respectively. The present research deals with offering two solutions for this problem. The original idea of the present research is using changeable learning rate at each state of training phase in the CMAC model. The first algorithm deals with a new learning rate based on reviation of learning rate. The second algorithm deals with number of training iteration and performance learning, with respect to this fact that error is compatible with inverse training time. Simulation results show that this algorithms have faster convergence and better performance in comparison to conventional CMAC model in all training cycles.https://jacet.srbiau.ac.ir/article_6107_aaa4c27e8f25242fed342b4f25718026.pdfcmaclearning ratetraining iterationlearning performance
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Nazal Modhej Mohammad Teshnehlab Mashallah Abbasi Dezfouli
spellingShingle	Nazal Modhej Mohammad Teshnehlab Mashallah Abbasi Dezfouli Two Novel Learning Algorithms for CMAC Neural Network Based on Changeable Learning Rate Journal of Advances in Computer Engineering and Technology cmac learning rate training iteration learning performance
author_facet	Nazal Modhej Mohammad Teshnehlab Mashallah Abbasi Dezfouli
author_sort	Nazal Modhej
title	Two Novel Learning Algorithms for CMAC Neural Network Based on Changeable Learning Rate
title_short	Two Novel Learning Algorithms for CMAC Neural Network Based on Changeable Learning Rate
title_full	Two Novel Learning Algorithms for CMAC Neural Network Based on Changeable Learning Rate
title_fullStr	Two Novel Learning Algorithms for CMAC Neural Network Based on Changeable Learning Rate
title_full_unstemmed	Two Novel Learning Algorithms for CMAC Neural Network Based on Changeable Learning Rate
title_sort	two novel learning algorithms for cmac neural network based on changeable learning rate
publisher	Science and Research Branch,Islamic Azad University
series	Journal of Advances in Computer Engineering and Technology
issn	2423-4192 2423-4206
publishDate	2015-02-01
description	Cerebellar Model Articulation Controller Neural Network is a computational model of cerebellum which acts as a lookup table. The advantages of CMAC are fast learning convergence, and capability of mapping nonlinear functions due to its local generalization of weight updating, single structure and easy processing. In the training phase, the disadvantage of some CMAC models is unstable phenomenon or slower convergence speed due to larger fixed or smaller fixed learning rate respectively. The present research deals with offering two solutions for this problem. The original idea of the present research is using changeable learning rate at each state of training phase in the CMAC model. The first algorithm deals with a new learning rate based on reviation of learning rate. The second algorithm deals with number of training iteration and performance learning, with respect to this fact that error is compatible with inverse training time. Simulation results show that this algorithms have faster convergence and better performance in comparison to conventional CMAC model in all training cycles.
topic	cmac learning rate training iteration learning performance
url	https://jacet.srbiau.ac.ir/article_6107_aaa4c27e8f25242fed342b4f25718026.pdf
work_keys_str_mv	AT nazalmodhej twonovellearningalgorithmsforcmacneuralnetworkbasedonchangeablelearningrate AT mohammadteshnehlab twonovellearningalgorithmsforcmacneuralnetworkbasedonchangeablelearningrate AT mashallahabbasidezfouli twonovellearningalgorithmsforcmacneuralnetworkbasedonchangeablelearningrate
_version_	1716827843232530432

Two Novel Learning Algorithms for CMAC Neural Network Based on Changeable Learning Rate

Similar Items