Journal
PHYSICA D-NONLINEAR PHENOMENA
Volume 421, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.physd.2021.132882
Keywords
Reservoir computing; Liquid state machine; Time series analysis; Lorenz equations; Delay embedding; Recurrent neural networks
Categories
Funding
- EPSRC, UK Centre for Doctoral Training in Statistical Applied Mathematics at Bath (SAMBa) [EP/L015684/1]
Ask authors/readers for more resources
Echo State Networks (ESNs) are single-layer recurrent neural networks trained by regularised linear least squares regression, which can approximate target functions effectively. The numerical experiments on the Lorenz system demonstrate the validity and feasibility of ESN.
Echo State Networks (ESNs) are a class of single-layer recurrent neural networks with randomly generated internal weights, and a single layer of tuneable outer weights, which are usually trained by regularised linear least squares regression. Remarkably, ESNs still enjoy the universal approximation property despite the training procedure being entirely linear. In this paper, we prove that an ESN trained on a sequence of observations from an ergodic dynamical system (with invariant measure mu) using Tikhonov least squares regression against a set of targets, will approximate the target function in the L-2(mu) norm. In the special case that the targets are future observations, the ESN is learning the next step map, which allows time series forecasting. We demonstrate the theory numerically by training an ESN using Tikhonov least squares on a sequence of scalar observations of the Lorenz system. (C) 2021 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available