On Simulation Performance of Feedforward and NARX Networks Under Different Numerical Training Algorithms
Salim Lahmiri · Advances in systems analysis, software engineering, and high performance computing book series · 2015
This chapter focuses on comparing the forecasting ability of the backpropagation neural network (BPNN) and the nonlinear autoregressive moving average with exogenous inputs (NARX) network trained with different algorithms; namely the quasi-Newton (Broyden-Fletcher-Goldfarb-Shanno, BFGS), conjugate gradient (Fletcher-Reeves update, Polak-Ribiére update, Powell-Beale restart), and Levenberg-Marquardt algorithm. Three synthetic signals are generated to conduct experiments. The simulation results showed that in general the NARX which is a dynamic system outperforms the popular BPNN. In addition, conjugate gradient algorithms provide better prediction accuracy than the Levenberg-Marquardt algorithm widely used in the literature in modeling exponential signal. However, the LM performed the best when used for forecasting the Moroccan and South African stock price indices under both the BPNN and NARX systems.