An extended Elman net for modeling time series

Abstract

The prediction and modeling of dynamical systems, for example chaotic time series, with neural networks remains an interesting and challenging research problem. It seems to be rather natural to employ recurrent neural networks for which we will suggest a new structure based on the Elman net [1]. The major difference to neural networks as proposed by Williams and Zipser [2] is the way we organize the time steps. The dynamic of the network and of the input flow is defined in a way as to guarantee that the information at the input node is available at the output node in one time step, irrespective of the connection matrix. We apply the network to the Lorenz and the Rössler system and comment on the problem of evaluating the quality of a network used as a dynamical model.