Echo State Networks: analysis, training and predictive control
Abstract
The goal of this paper is to investigate the theoretical properties, the training algorithm, and the predictive control applications of Echo State Networks (ESNs), a particular kind of Recurrent Neural Networks. First, a condition guaranteeing incremetal global asymptotic stability is devised. Then, a modified training algorithm allowing for dimensionality reduction of ESNs is presented. Eventually, a model predictive controller is designed to solve the tracking problem, relying on ESNs as the model of the system. Numerical results concerning the predictive control of a nonlinear process for pH neutralization confirm the effectiveness of the proposed algorithms for the identification, dimensionality reduction, and the control design for ESNs.
Cite
@article{arxiv.1902.01618,
title = {Echo State Networks: analysis, training and predictive control},
author = {Luca Bugliari Armenio and Enrico Terzi and Marcello Farina and Riccardo Scattolini},
journal= {arXiv preprint arXiv:1902.01618},
year = {2019}
}
Comments
6 pages,5 figures, submitted to European Control Conference (ECC)