Recovering discrete delayed fractional equations from trajectories

Abstract

We show how machine learning methods can unveil the fractional and delayed nature of discrete dynamical systems. In particular, we study the case of the fractional delayed logistic map. We show that given a trajectory, we can detect if it has some delay effect or not, and also to characterize the fractional component of the underlying generation model.

arXiv comment14 pages, 9 figures

References in corpus (4)

• A Critical Review of Recurrent Neural Networks for Sequence Learning
• Nonergodic Subdiffusion from Brownian Motion in an Inhomogeneous Medium
• Classification, inference and segmentation of anomalous diffusion with recurrent neural networks
• Characterization of anomalous diffusion classical statistics powered by deep learning (CONDOR)