%0 Conference Paper
%A Izzeldin, H.
%A Asirvadam, V.S.
%A Saad, N.
%D 2012
%F scholars:2971
%K Auto-regressive; Conjugate gradient; Convergence rates; External input; Irregular sampling; Learning approach; MLP neural networks; Model order; Multi layer perceptron; Neural network learning; Random loss; Real time; Sliding-window, Conjugate gradient method; Neural networks; Signal processing, Backpropagation
%P 115-119
%R 10.1109/CSPA.2012.6194702
%T Real time neural network learning with lost packets using sliding window approaches
%U https://khub.utp.edu.my/scholars/2971/
%X This paper presents real time nonlinear system identification with irregular sampling time or lost packets. This work views the performance of predictive MLP neural network using sliding window learning approach. By adopting nonlinear autoregressive with external input (NARX) model order, this paper investigate the response of sliding window leaning when the measurement received by the MLP network are susceptible to random loss. The simulation results show that the sliding window approach yields good convergence despite the information being lost overtime. The paper concludes that result obtained from sliding window conjugate gradient (with Dai and Yuan variant) has the best convergence rate. © 2012 IEEE.
%Z cited By 1; Conference of 2012 IEEE 8th International Colloquium on Signal Processing and Its Applications, CSPA 2012 ; Conference Date: 23 March 2012 Through 25 March 2012; Conference Code:89941