Studying the effect of training Levenberg Marquardt neural network by using hybrid meta-heuristic algorithms

Studying the effect of training Levenberg Marquardt neural network by using hybrid meta-heuristic algorithms

Accelerated Particle Swarm Optimization (APSO) algorithm is one of the latest additions to the group of meta-heuristic nature inspired algorithms which provides derivative-free solutions to solve complex problems. Meanwhile, the Levenberg Marquardt Back propagation (LMBP) still it is not able to...

Full description

Bibliographic Details
Main Authors: Abubakar, Adamu, Khan, Abdullah, Nawi, Nazri Mohd, Rehman, M. Z., Teh , Ying Wah, Chiroma , Haruna, Herawan, Tutut
Format: Article
Language:English
English
Published: American Scientific Publishers 2016
Subjects:
QA76 Computer software
Online Access:http://irep.iium.edu.my/51019/
http://irep.iium.edu.my/51019/
http://irep.iium.edu.my/51019/
http://irep.iium.edu.my/51019/1/Attach_Lavenberg.pdf
http://irep.iium.edu.my/51019/4/51019-Studying_the_effect_of_training_levenberg_marquardt_neural_network_by_using_hybrid_meta-heuristic_algorithms_SCOPUS.pdf
id iium-51019
recordtype eprints
spelling iium-510192016-08-03T00:37:16Z http://irep.iium.edu.my/51019/ Studying the effect of training Levenberg Marquardt neural network by using hybrid meta-heuristic algorithms Abubakar, Adamu Khan, Abdullah Nawi, Nazri Mohd Rehman, M. Z. Teh , Ying Wah Chiroma , Haruna Herawan, Tutut QA76 Computer software Accelerated Particle Swarm Optimization (APSO) algorithm is one of the latest additions to the group of meta-heuristic nature inspired algorithms which provides derivative-free solutions to solve complex problems. Meanwhile, the Levenberg Marquardt Back propagation (LMBP) still it is not able to avoid local minimum. To deal with this problem, global search optimization technique has the ability to adjust the weight for NN (Neural Network) to avoid the local minima problem. This paper proposes an accelerated particle swarm optimization (APSO) is implemented in conjunction with Levenberg Marquardt back propagation (LMBP) algorithms to achieve faster convergence rate and to avoid local minima problem. The performances of the proposed Accelerated Particle Swarm Optimization Levenberg Marquardt (APSO_LM) algorithms compared by means of simulations on 7-Bit Parity and six UCI benchmark classification datasets. The simulation results show that the APSO-LM algorithm shows better performance than baseline algorithms in terms of convergence speed and Mean Squared Error (MSE). American Scientific Publishers 2016-01 Article PeerReviewed application/pdf en http://irep.iium.edu.my/51019/1/Attach_Lavenberg.pdf application/pdf en http://irep.iium.edu.my/51019/4/51019-Studying_the_effect_of_training_levenberg_marquardt_neural_network_by_using_hybrid_meta-heuristic_algorithms_SCOPUS.pdf Abubakar, Adamu and Khan, Abdullah and Nawi, Nazri Mohd and Rehman, M. Z. and Teh , Ying Wah and Chiroma , Haruna and Herawan, Tutut (2016) Studying the effect of training Levenberg Marquardt neural network by using hybrid meta-heuristic algorithms. Journal of Computational and Theoretical Nanoscience, 13 (1). pp. 450-460. ISSN 1546-1955 E-ISSN 1546-1963 http://www.ingentaconnect.com/contentone/asp/jctn/2016/00000013/00000001/art00066 10.1166/jctn.2016.4826
repository_type Digital Repository
institution_category Local University
institution International Islamic University Malaysia
building IIUM Repository
collection Online Access
language English
English
topic QA76 Computer software
spellingShingle QA76 Computer software
Abubakar, Adamu
Khan, Abdullah
Nawi, Nazri Mohd
Rehman, M. Z.
Teh , Ying Wah
Chiroma , Haruna
Herawan, Tutut
Studying the effect of training Levenberg Marquardt neural network by using hybrid meta-heuristic algorithms
description Accelerated Particle Swarm Optimization (APSO) algorithm is one of the latest additions to the group of meta-heuristic nature inspired algorithms which provides derivative-free solutions to solve complex problems. Meanwhile, the Levenberg Marquardt Back propagation (LMBP) still it is not able to avoid local minimum. To deal with this problem, global search optimization technique has the ability to adjust the weight for NN (Neural Network) to avoid the local minima problem. This paper proposes an accelerated particle swarm optimization (APSO) is implemented in conjunction with Levenberg Marquardt back propagation (LMBP) algorithms to achieve faster convergence rate and to avoid local minima problem. The performances of the proposed Accelerated Particle Swarm Optimization Levenberg Marquardt (APSO_LM) algorithms compared by means of simulations on 7-Bit Parity and six UCI benchmark classification datasets. The simulation results show that the APSO-LM algorithm shows better performance than baseline algorithms in terms of convergence speed and Mean Squared Error (MSE).
format Article
author Abubakar, Adamu
Khan, Abdullah
Nawi, Nazri Mohd
Rehman, M. Z.
Teh , Ying Wah
Chiroma , Haruna
Herawan, Tutut
author_facet Abubakar, Adamu
Khan, Abdullah
Nawi, Nazri Mohd
Rehman, M. Z.
Teh , Ying Wah
Chiroma , Haruna
Herawan, Tutut
author_sort Abubakar, Adamu
title Studying the effect of training Levenberg Marquardt neural network by using hybrid meta-heuristic algorithms
title_short Studying the effect of training Levenberg Marquardt neural network by using hybrid meta-heuristic algorithms
title_full Studying the effect of training Levenberg Marquardt neural network by using hybrid meta-heuristic algorithms
title_fullStr Studying the effect of training Levenberg Marquardt neural network by using hybrid meta-heuristic algorithms
title_full_unstemmed Studying the effect of training Levenberg Marquardt neural network by using hybrid meta-heuristic algorithms
title_sort studying the effect of training levenberg marquardt neural network by using hybrid meta-heuristic algorithms
publisher American Scientific Publishers
publishDate 2016
url http://irep.iium.edu.my/51019/
http://irep.iium.edu.my/51019/
http://irep.iium.edu.my/51019/
http://irep.iium.edu.my/51019/1/Attach_Lavenberg.pdf
http://irep.iium.edu.my/51019/4/51019-Studying_the_effect_of_training_levenberg_marquardt_neural_network_by_using_hybrid_meta-heuristic_algorithms_SCOPUS.pdf
first_indexed 2023-09-18T21:12:11Z
last_indexed 2023-09-18T21:12:11Z
_version_ 1777411326604214272

Similar Items