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. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/icassp.2019.8683447 | 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) |
Keywords | Field | DocType |
Dynamical systems, Data-driven models, Neural networks, Forecasting, Runge-Kutta methods | Training set,Residual,Runge–Kutta methods,Architecture,Pattern recognition,Computer science,Dynamical systems theory,Artificial intelligence,Sampling (statistics),Chaotic,Artificial neural network | Conference |
ISSN | Citations | PageRank |
1520-6149 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Said Ouala | 1 | 4 | 2.43 |
Ananda Pascual | 2 | 4 | 4.91 |
Ronan Fablet | 3 | 3 | 2.84 |