Universiti Teknologi Malaysia Institutional Repository

Enhancement of particle swarm optimization in Elman recurrent network with bounded Vmax function

Aziz, Mohamad Firdaus Ab. and Shamsuddin, Siti Mariya and Alwee, Razana (2009) Enhancement of particle swarm optimization in Elman recurrent network with bounded Vmax function. In: 2009 Third Asia International Conference on Modelling & Simulation. Article number 5071970 . IEEE, pp. 125-130. ISBN 978-076953648-4

Full text not available from this repository.

Official URL: http://dx.doi.org/10.1109/AMS.2009.90

Abstract

As the widespread modus operandi in real applications, Backpropagation(BP) in Recurrent Neural Networks (RNN) is computationally more powerful than standard feedforward neural networks. In principle, RNN can implement almost any arbitrary sequential behavior. However, there are many drawbacks in BP network, for instance, confinement in finding local minimum and may get stuck at regions of a search space or trap in local minima. To solve these problems, various optimization techniques such as Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) have been executed to improve ANN performance. In this study, we exploit errors optimization of Elman Recurrent Network with Particle Swarm Optimization (ERNPSO) to probe the performance of both networks with bounded Vmax function. Main characteristics of Vmax function are to control the global exploration of particles in PSO. The results show that ERNPSO with bounded Vmax of hyperbolic tangent furnishes promising outcomes in terms of classification accuracy and convergence rate compared to bounded Vmax sigmoid function and standard Vmax function.

Item Type:Book Section
Additional Information:2009 3rd Asia International Conference on Modelling and Simulation, AMS 2009; Bandung, Bali; 25 May 2009 through 26 May 2009
Uncontrolled Keywords:artificial neural network, backpropagation network, Elman recurrent network, particle swarm optimization, recurrent network
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:Computer Science and Information System
ID Code:14115
Deposited By: Zalinda Shuratman
Deposited On:26 Aug 2011 04:50
Last Modified:26 Aug 2011 04:50

Repository Staff Only: item control page