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

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

	PDF - Published Version Restricted to Repository staff only Download (4MB) | Request a copy
	PDF (SCOPUS) - Published Version Restricted to Repository staff only Download (323kB) | Request a copy

Abstract

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).

Item Type:	Article (Journal)
Additional Information:	7132/51019
Uncontrolled Keywords:	Particle Swarm Optimization, LevenbergMarquardt Back Propagation, Local Minima, Data Classification, Nature Inspired Algorithms.
Subjects:	Q Science > QA Mathematics > QA76 Computer software
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Information and Communication Technology > Department of Information System Kulliyyah of Information and Communication Technology > Department of Information System
Depositing User:	Dr Adamu Abubakar
Date Deposited:	03 Aug 2016 08:36
Last Modified:	03 Aug 2016 08:37
URI:	http://irep.iium.edu.my/id/eprint/51019

Actions (login required)

View Item