Excellence in Research and Innovation for Humanity
%0 Journal Article
%A Abiodun M. Aibinu and  Momoh J. E. Salami and  Amir A. Shafie and  Athaur Rahman Najeeb
%D 2008 
%J  International Journal of Computer, Electrical, Automation, Control and Information Engineering
%B World Academy of Science, Engineering and Technology
%I International Science Index 18, 2008
%T Increasing The Speed of Convergence of an Artificial Neural Network based ARMA Coefficients Determination Technique
%U http://waset.org/publications/3015
%V 18
%X 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
%P 1839 - 1845