Increasing the speed of convergence of an artificial neural network based ARMA coefficients determination technique

Aibinu, Abiodun Musa and Salami, Momoh Jimoh Emiyoka and Shafie, Amir Akramin and Najeeb, Athaur Rahman (2008) Increasing the speed of convergence of an artificial neural network based ARMA coefficients determination technique. In: International Conference on Computer System Engineering (ICCSE) .

Preview

PDF - Published Version Download (441kB) | Preview

Abstract

In this paper, novel techniques in increasing the accuracy and speed of convergence of a Feed forward Back propagation Artificial Neural Network (FFBPNN) with polynomial activation function reported in literature is presented. These technique was subsequently used to determine the coefficients of Autoregressive Moving Average (ARMA) and Autoregressive (AR) system. The results obtained by introducing sequential and batch method of weight initialization, batch method of weight and coefficient update, adaptive momentum and learning rate technique gives more accurate result and significant reduction in convergence time when compared t the traditional method of back propagation algorithm, thereby making FFBPNN an appropriate technique for online ARMA coefficient determination.

Item Type:	Conference or Workshop Item (Full Paper)
Additional Information:	6472/5451
Uncontrolled Keywords:	Adaptive Learning rate, Adaptive momentum, Autoregressive, Modeling, Neural Network
Subjects:	T Technology > T Technology (General)
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Engineering > Department of Mechatronics Engineering
Depositing User:	Dr Abiodun Musa Aibinu
Date Deposited:	11 Jun 2012 14:53
Last Modified:	11 Jun 2012 14:53
URI:	http://irep.iium.edu.my/id/eprint/5451

Actions (login required)

View Item