Home Page

Papers

Submissions

News

Editorial Board

Special Issues

Open Source Software

Proceedings (PMLR)

Data (DMLR)

Transactions (TMLR)

Search

Statistics

Login

Frequently Asked Questions

Contact Us



RSS Feed

The Asymptotic Performance of Linear Echo State Neural Networks

Romain Couillet, Gilles Wainrib, Harry Sevi, Hafiz Tiomoko Ali; 17(178):1−35, 2016.

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.

[abs][pdf][bib]       
© JMLR 2016. (edit, beta)

Mastodon