The Asymptotic Performance of Linear Echo State Neural Networks
Abstract
In this article, a study of the mean-square error (MSE) performance of linear echo-state neural networks is performed, both for training and testing tasks. Considering the realistic setting of noise present at the network nodes, we derive deterministic equivalents for the aforementioned MSE in the limit where the number of input data $T$ and network size $n$ both grow large. Specializing then the network connectivity matrix to specific random settings, we further obtain simple formulas that provide new insights on the performance of such networks.
Cite
Text
Couillet et al. "The Asymptotic Performance of Linear Echo State Neural Networks." Journal of Machine Learning Research, 2016.Markdown
[Couillet et al. "The Asymptotic Performance of Linear Echo State Neural Networks." Journal of Machine Learning Research, 2016.](https://mlanthology.org/jmlr/2016/couillet2016jmlr-asymptotic/)BibTeX
@article{couillet2016jmlr-asymptotic,
title = {{The Asymptotic Performance of Linear Echo State Neural Networks}},
author = {Couillet, Romain and Wainrib, Gilles and Sevi, Harry and Ali, Hafiz Tiomoko},
journal = {Journal of Machine Learning Research},
year = {2016},
pages = {1-35},
volume = {17},
url = {https://mlanthology.org/jmlr/2016/couillet2016jmlr-asymptotic/}
}