We consider arbitrary bounded discrete time series originating from dynamical system with recursivity. More precisely, we provide an explicit construction of recurrent neural networks which effectively approximate the corresponding discrete dynamical systems.
Cite
@article{arxiv.2409.19278,
title = {Explicit construction of recurrent neural networks effectively approximating discrete dynamical systems},
author = {Chikara Nakayama and Tsuyoshi Yoneda},
journal= {arXiv preprint arXiv:2409.19278},
year = {2024}
}