2009 | OriginalPaper | Buchkapitel
New Approach of Recurrent Neural Network Weight Initialization
verfasst von : Roberto Marichal, J. D. PiÑeiro, E. J. González, J. M. Torres
Erschienen in: Advances in Computational Algorithms and Data Analysis
Verlag: Springer Netherlands
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
This paper proposes a weight initialization strategy for a discrete—time re current neural network model. It is based on analyzing the recurrent network as a nonlinear system, and choosing its initial weights to put this system in the bound aries between different dynamics, i.e., its bifurcations. The relationship between the change in dynamics and training error evolution is studied. Two simple examples of the application of this strategy are shown: the identification of DC Induction motor and the detection of a physiological signal, a feature of a visual evoked potential brain signal.