Dimension of Reservoir Computers
Adaptation and Self-Organizing Systems
2020-01-07 v1 Machine Learning
Neural and Evolutionary Computing
Machine Learning
Abstract
A reservoir computer is a complex dynamical system, often created by coupling nonlinear nodes in a network. The nodes are all driven by a common driving signal. In this work, three dimension estimation methods, false nearest neighbor, covariance and Kaplan-Yorke dimensions, are used to estimate the dimension of the reservoir dynamical system. It is shown that the signals in the reservoir system exist on a relatively low dimensional surface. Changing the spectral radius of the reservoir network can increase the fractal dimension of the reservoir signals, leading to an increase in testing error.
Cite
@article{arxiv.1912.06472,
title = {Dimension of Reservoir Computers},
author = {Thomas L. Carroll},
journal= {arXiv preprint arXiv:1912.06472},
year = {2020}
}
Comments
submitted to Chaos