Multi-step-ahead Prediction with Neural Networks : a Review

We review existing approaches in using neural networks for solving multi -step-ahead prediction problems. A few experiments allow us to further explore the relationship between the abilit y to learn longer-range dependencies and performance in multi -stepahead prediction. We eventually focus on characteristics of various multi -step-ahead prediction problems that encourage us to prefer one method over another.

[1]  G. Yule.  On a Method of Investigating Periodicities in Disturbed Series, with Special Reference to Wolfer's Sunspot Numbers , 1927 .

[2]  L. Glass,et al.  Oscillation and chaos in physiological control systems. , 1977, Science.

[3]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[4]  David E. Rumelhart,et al.  Predicting the Future: a Connectionist Approach , 1990, Int. J. Neural Syst..

[5]  Thomas Martinetz,et al.  'Neural-gas' network for vector quantization and its application to time-series prediction , 1993, IEEE Trans. Neural Networks.

[6]  Eric A. Wan,et al.  Finite impulse response neural networks with applications in time series prediction , 1994 .

[7]  Yoshua Bengio,et al.  Hierarchical Recurrent Neural Networks for Long-Term Dependencies , 1995, NIPS.

[8]  J. Suykens,et al.  Learning a simple recurrent neural state space model to behave like Chua's double scroll , 1995 .

[9]  Thomas Czernichow.  Apport des reseaux recurrents a la prevision de series temporelles, applications a la prevision de consommation d'electricite , 1996 .

[10]  Peter Tiño,et al.  Learning long-term dependencies in NARX recurrent neural networks , 1996, IEEE Trans. Neural Networks.

[11]  Amir F. Atiya,et al.  A comparison between neural-network forecasting techniques-case study: river flow forecasting , 1999, IEEE Trans. Neural Networks.

[12]  Johan A. K. Suykens,et al.  WINNING ENTRY OF THE K. U. LEUVEN TIME-SERIES PREDICTION COMPETITION , 1999 .

[13]  Nathan Intrator,et al.  Boosting Regression Estimators , 1999, Neural Computation.

[14]  Amir F. Atiya,et al.  Multi-step-ahead prediction using dynamic recurrent neural networks , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[15]  Local Modeling Optimization for Time Series Prediction , 2000 .

[16]  R. Bone,et al.  Two constructive algorithms for improved time series processing with recurrent neural networks , 2000, Neural Networks for Signal Processing X. Proceedings of the 2000 IEEE Signal Processing Society Workshop (Cat. No.00TH8501).

[17]  J. Suykens,et al.  Recurrent least squares support vector machines , 2000 .

[18]  Jürgen Schmidhuber,et al.  Applying LSTM to Time Series Predictable through Time-Window Approaches , 2000, ICANN.

[19]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .

[20]  Johan A. K. Suykens,et al.  Improved Long-Term Temperature Prediction by Chaining of Neural Networks , 2001, Int. J. Neural Syst..

[21]  Jean Pierre Asselin de Beauville,et al.  Learning long-term dependencies by the selective addition of time-delayed connections to recurrent neural networks , 2002, Neurocomputing.