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

Abubakar, Adamu I. and Khan, Abdullah and Mohd Nawi, Nazri and Rehman, M. Z. and Teh , Ying Wah and Haruna , Chiroma 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.

Full text not available from this repository.

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
Uncontrolled Keywords:Particle swarm optimization; Levenberg Marquardt back propagation; local minima; data classification; nature inspired algorithms
Subjects:Q Science > QA Mathematics > QA76 Computer software
Divisions:Faculty of Computer Science and Information Technology > Department of Software Engineering
ID Code:8554
Deposited By:Mr. Mohammad Shaifulrip Ithnin
Deposited On:03 Jul 2017 08:54
Last Modified:03 Jul 2017 08:54

Repository Staff Only: item control page