Echo state networks are universal

06/03/2018
by   Lyudmila Grigoryeva, et al.
0

This paper shows that echo state networks are universal uniform approximants in the context of discrete-time fading memory filters with uniformly bounded inputs defined on negative infinite times. The proof uses newly introduced internal approximation results for filters associated to reservoir computing systems, as well as the external approximation properties of state affine systems proved in a previous work.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/03/2017

Universal discrete-time reservoir computers with stochastic inputs and linear readouts using non-homogeneous state-affine systems

A new class of non-homogeneous state-affine systems is introduced. Suffi...
research
10/22/2020

Fading memory echo state networks are universal

Echo state networks (ESNs) have been recently proved to be universal app...
research
07/07/2018

Reservoir Computing Universality With Stochastic Inputs

The universal approximation properties with respect to L ^p -type criter...
research
02/16/2019

Differentiable reservoir computing

Much effort has been devoted in the last two decades to characterize the...
research
09/17/2020

Discrete-time signatures and randomness in reservoir computing

A new explanation of geometric nature of the reservoir computing phenome...
research
09/16/2022

Transport in reservoir computing

Reservoir computing systems are constructed using a driven dynamical sys...
research
03/30/2021

Uniform Envelopes

In the author's PhD thesis (2019) universal envelopes were introduced as...

Please sign up or login with your details

Forgot password? Click here to reset