Inferring the fractional nature of Wu Baleanu trajectories
-
Published:2023-05-09
Issue:13
Volume:111
Page:12421-12431
-
ISSN:0924-090X
-
Container-title:Nonlinear Dynamics
-
language:en
-
Short-container-title:Nonlinear Dyn
Author:
Conejero J. AlbertoORCID, Garibo-i-Orts ÒscarORCID, Lizama CarlosORCID
Abstract
AbstractWe infer the parameters of fractional discrete Wu Baleanu time series by using machine learning architectures based on recurrent neural networks. Our results shed light on how clearly one can determine that a given trajectory comes from a specific fractional discrete dynamical system by estimating the fractional exponent and the growth parameter $$\mu $$
μ
. With this example, we also show how machine learning methods can be incorporated into the study of fractional dynamical systems.
Funder
Ministerio de Ciencia e Innovación Universitat Politècnica de València FONDECYT
Publisher
Springer Science and Business Media LLC
Subject
Electrical and Electronic Engineering,Applied Mathematics,Mechanical Engineering,Ocean Engineering,Aerospace Engineering,Control and Systems Engineering
Reference37 articles.
1. Argun, A., Volpe, G., Bo, S.: Classification, inference and segmentation of anomalous diffusion with recurrent neural networks. J. Phys. A Math. Theor. 54(29), 294003 (2021) 2. Brownlee, J.: Long Short-Term Memory Networks with Python. eBook (2017) 3. Conejero, J., Lizama, C., Mira-Iglesias, A., Rodero, C.: Visibility graphs of fractional Wu-Baleanu time series. J. Differ. Equ. Appl. 25(9–10), 1321–1331 (2019) 4. Cun, Y., Boser, B., Denker, J., Howard, R., Habbard, W., Jackel, L., Henderson, D.: Handwritten Digit Recognition with a Back-propagation Network, pp. 396–404. Morgan Kaufmann Publishers Inc, San Francisco (1990) 5. Fawzi, A., Balog, M., Huang, A., Hubert, T., Romera-Paredes, B., Barekatain, M., Novikov, A., Ruiz, F., Schrittwieser, J., Swirszcz, G., et al.: Discovering faster matrix multiplication algorithms with reinforcement learning. Nature 610(7930), 47–53 (2022)
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
|
|