Adaptive Weighted Performance Criterion for Artificial Neural Networks

Abstract

Extended Weighted Performance Criterion (EWPC) which is motivated from Weighted Information Criterion (WIC) has been shown promising results in previous study and results of the application showed that EWPC is capable of giving noticeable performance among other measures. EWPC includes MSE, RMSE, R4MS4E, MAPE, MAE, GMAE, MdAE, MdAPE, NS, MRAE, MdRAE, GMRAE, RMSPE, RMdSPE, SMAPE, SMdAPE, MSMAPE, MASE, and RMSSE with fixed coefficients. In this study, we attempt to improve the performance of EWPC by using adaptive coefficients. The application study which consists of several simulated and real-world time series data is utilized for showing the performance of the criterion. Comparisons of the results show that Adaptive Weighted Performance Criterion (AWPC) is quite preferable as a consistent measure for model selection in Artificial Neural Networks.