Fading memory echo state networks are universal

10/22/2020
by   Lukas Gonon, et al.
0

Echo state networks (ESNs) have been recently proved to be universal approximants for input/output systems with respect to various L ^p-type criteria. When 1≤ p< ∞, only p-integrability hypotheses need to be imposed, while in the case p=∞ 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/03/2018

Echo state networks are universal

This paper shows that echo state networks are universal uniform approxim...
research
07/07/2018

Reservoir Computing Universality With Stochastic Inputs

The universal approximation properties with respect to L ^p -type criter...
research
08/02/2023

A Universal Birkhoff Theory for Fast Trajectory Optimization

Over the last two decades, pseudospectral methods based on Lagrange inte...
research
01/07/2019

Learning Nonlinear Input-Output Maps with Dissipative Quantum Systems

In this paper, we develop a theory of learning nonlinear input-output ma...
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
02/16/2019

Differentiable reservoir computing

Much effort has been devoted in the last two decades to characterize the...
research
07/23/2020

Dimension reduction in recurrent networks by canonicalization

Many recurrent neural network machine learning paradigms can be formulat...

Please sign up or login with your details

Forgot password? Click here to reset