No confident code implementation found for this paper.
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.
No confident code match yet
We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.
No code implementations found yet.
Know of an implementation? Let us know in the comments below!
Liquid Time-constant Networks
Continuous-Time Piecewise-Linear Recurrent Neural Networks
PAC-Bayes Generalisation Bounds for Dynamical Systems Including Stable RNNs
Efficient Time-Series Approximation with Linear Recurrent Neural Networks: Architecture Learning and Predictive Power
Metric-Entropy Limits on the Approximation of Nonlinear Dynamical Systems
Gradient-free training of recurrent neural networks
@article{nakayama2024explicit,
title = {Explicit construction of recurrent neural networks effectively approximating discrete dynamical systems},
author = {Chikara Nakayama and Tsuyoshi Yoneda},
year = {2024},
eprint = {2409.19278},
archivePrefix = {arXiv},
url = {http://arxiv.org/abs/2409.19278v1}
}Shows whether official code is linked for this paper.
[](https://codeofpaper.com/paper/2409.19278)