%0 Journal Article
%@ 18761100
%A Asirvadam, V.S.
%A Izzeldin, H.T.A.
%A Saad, N.
%A Mcloone, S.F.
%C Macau
%D 2012
%F scholars:3095
%J Lecture Notes in Electrical Engineering
%K Conjugate gradient; Convergence performance; Correlated data; Data store; Distance measure; Higher order; Learning strategy; multilayer perceptron; Multilayer perceptron neural networks; Prediction errors; Semi-batch; Sliding-window; sliding-window learning; Store management, Backpropagation; Conjugate gradient method; Covariance matrix; Electronics engineering; Electronics industry; Industrial applications; Information technology; Learning algorithms; Multilayers; Neural networks, Information management
%P 61-67
%R 10.1007/978-3-642-26001-8₉
%T Semi batch learning with store management using enhanced conjugate gradient
%U https://khub.utp.edu.my/scholars/3095/
%V 136 LN
%X This paper explores the performance of sliding-window based training, termed as semi batch, using multilayer perceptron (MLP) neural network in the presence of correlated data. The sliding window training is a form of higher order instantaneous learning strategy without the need of covariance matrix, usually employed for modeling and tracking purposes. Sliding-window framework is implemented to combine the robustness of offline learning algorithms with the ability to track online the underlying process of a function. This paper adopted sliding window training with recent advances in conjugate gradient direction with application of data store management e.g. simple distance measure, angle evaluation and the novel prediction error test. The simulation results show the best convergence performance is gained by using store management techniques. © 2012 Springer-Verlag.
%Z cited By 0; Conference of 2nd International Conference of Electrical and Electronics Engineering, ICEEE 2011 ; Conference Date: 1 December 2011 Through 2 December 2011; Conference Code:88163