Carlos E. Pedreira, Marcelo C. Medeiros
This paper studies the performance of neural networks estimated with Bayesian regularization to model and forecast time series where the data generating process is in fact linear. A simulation experiment is carried out to compare the forecasts made by linear autoregressive models and neural networks. Keywords: Neural networks, Bayesian regularization, nonlinear forecasting, nonlinear time series
© 2001-2024 Fundación Dialnet · Todos los derechos reservados