Prediction of chaotic time series using recurrent neural networks
- 2 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
In this paper, we propose to train and use a recurrent artificial neural network(ANN) to predict a chaotic time series. Instead of predicting the next sample in the time series as is normally done, the neural network is trained to produce the sequence that follows a given initial condition. Dynamical parameters from the time series provide the clue in deciding the length of these training sequences. The proposed method has been applied to predicting both periodic and chaotic time series, and is superior to the conventional ANN approach.Keywords
This publication has 6 references indexed in Scilit:
- PREDICTION OF CHAOTIC TIME SERIES WITH NEURAL NETWORKS AND THE ISSUE OF DYNAMIC MODELINGInternational Journal of Bifurcation and Chaos, 1992
- PREDICTING THE FUTURE: A CONNECTIONIST APPROACHInternational Journal of Neural Systems, 1990
- A Learning Algorithm for Continually Running Fully Recurrent Neural NetworksNeural Computation, 1989
- Nonlinear prediction of chaotic time seriesPhysica D: Nonlinear Phenomena, 1989
- Determining Lyapunov exponents from a time seriesPhysica D: Nonlinear Phenomena, 1985
- Oscillation and Chaos in Physiological Control SystemsScience, 1977