ALL libraries (COBIB.SI union bibliographic/catalogue database)
  • Prediction of dynamical phenomena by a neural network
    Grabec, Igor
    The article describes an adaptive information processing system capable of predicting dynamical phenomena. It includes a neural network-like memory, a predictor, two shift registers, and a ... comparator. In the memory an internal empirical model of observed phenomenon is formed. It is described by a set of memorized prototype transitions between successive states of input time dependent signal which can also be chaotic. The adaptation of prototypes corresponds to a self-organization process which maximally preserves information obtained by measurements. In the predictor the forthcoming signal is estimated from the prototypes. The system operation is demonstrated on a chaotic signal generated by the Henon map. By minimizing the prediction error, determined by the comparator, a proper embedding dimension of the chaotic attractor can be selected, while the Lyapunov coefficient can be estimated from the discrepancy between the predicted and the input signal.
    Source: Proceedings (Vol. 1, str. 18-23)
    Type of material - conference contribution
    Publish date - 1991
    Language - english
    COBISS.SI-ID - 4344347

source: Proceedings (Vol. 1, str. 18-23)
loading ...
loading ...
loading ...