Publication details.

Paper

Year:2019
Author(s):S. Ouala, A. Pascual. , R. Fablet
Title:Residual Integration Neural Network
Journal:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN:1939-1404
Pages:1
D.O.I.:10.1109/ICASSP.2019.8683447
Web:
Abstract:In this work, we investigate residual neural network representations for the identification and forecasting of dynamical systems. We propose a novel architecture that jointly learns the dynamical model and the associated Runge-Kutta integration scheme. We demonstrate the relevance of the proposed architecture with respect to learning-based state-of-the-art approaches in the identification and forecasting of chaotic dynamics when provided with training data with low temporal sampling rates.

Related staff

  • Ananda Pascual Ascaso
  • Related research groups

  • Marine Technologies, Operational and Coastal Oceanography