English

Fading memory echo state networks are universal

Neural and Evolutionary Computing 2020-10-26 v1

Abstract

Echo state networks (ESNs) have been recently proved to be universal approximants for input/output systems with respect to various LpL ^p-type criteria. When 1p<1\leq p< \infty, only pp-integrability hypotheses need to be imposed, while in the case p=p=\infty a uniform boundedness hypotheses on the inputs is required. This note shows that, in the last case, a universal family of ESNs can be constructed that contains exclusively elements that have the echo state and the fading memory properties. This conclusion could not be drawn with the results and methods available so far in the literature.

Keywords

Cite

@article{arxiv.2010.12047,
  title  = {Fading memory echo state networks are universal},
  author = {Lukas Gonon and Juan-Pablo Ortega},
  journal= {arXiv preprint arXiv:2010.12047},
  year   = {2020}
}

Comments

6 pages letter

R2 v1 2026-06-23T19:34:24.035Z