Residual Integration Neural Network - IMT Atlantique Access content directly
Conference Papers Year : 2019

Residual Integration Neural Network


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.
Fichier principal
Vignette du fichier
Integration_Residual_Net(1).pdf (463.58 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02005399 , version 1 (04-02-2019)



Said Ouala, Ananda Pascual, Ronan Fablet. Residual Integration Neural Network. ICASSP 2019 : IEEE International Conference on Acoustics, Speech and Signal Processing, May 2019, Brighton, United Kingdom. ⟨10.1109/ICASSP.2019.8683447⟩. ⟨hal-02005399⟩
123 View
778 Download



Gmail Facebook Twitter LinkedIn More