Ensemble encoding for time series forecasting with MLP networks

Neural networks represent a promising approach to time series forecasting; however, the problem of obtaining good network generalization continues to present a challenge. As a means of improving network generalization ability for time series forecasting applications, this paper investigates the utility of a biologically inspired scheme that employs receptive fields for encoding network inputs. Both single- and multi-step forecasting performances are studied in the context of the sunspot series. Additionally, a heuristic for selecting the placement and dilations of the receptive field functions is presented. The performance of multi-layered perceptron networks trained using the data arising from the encoding scheme is assessed. The heuristic for placing and dilating the receptive fields yielded networks that learn rapidly and have consistently good multi-step prediction capability as compared to other published results.

[1]  A. L. Beckman The Neural Basis of Behavior , 1982, Springer Netherlands.

[2]  Y. Shimakura,et al.  Short-term load forecasting using an artificial neural network , 1993, [1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems.

[3]  A. Lapedes,et al.  Nonlinear Signal Processing Using Neural Networks , 1987 .

[4]  Marie Cottrell,et al.  Neural modeling for time series: A statistical stepwise method for weight elimination , 1995, IEEE Trans. Neural Networks.

[5]  Tom Murray,et al.  Predicting sun spots using a layered perceptron neural network , 1996, IEEE Trans. Neural Networks.

[6]  E. W. Page,et al.  Optimizing locality of data representation in MLP networks , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[7]  H. Tong,et al.  Threshold Autoregression, Limit Cycles and Cyclical Data , 1980 .

[8]  Gene A. Tagliarini,et al.  Enhancing MLP networks using a distributed data representation , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[9]  Sridhar Narayan,et al.  Accelerating learning in a neural network for sonar signal classification , 1993, Defense, Security, and Sensing.

[10]  David E. Rumelhart,et al.  BACK-PROPAGATION, WEIGHT-ELIMINATION AND TIME SERIES PREDICTION , 1991 .