Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2021 Feb 15;379(2194):20200246. doi: 10.1098/rsta.2020.0246

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© 2021 The Authors.

Published by the Royal Society under the terms of the Creative Commons Attribution License http://creativecommons.org/licenses/by/4.0/, which permits unrestricted use, provided the original author and source are credited.

PMC Copyright notice

Figure 6. — Both plots are averages over 100 trials. (a) Lorenz 96 performance across varying algorithms. The direct polynomial regression outperforms both types of ESNs. The horizontal line at 0.3 is used as a standard measure of error for L96 to determine when a surrogate fails. (b) Modified Chua Task Performance across varying algorithms. The HSR ESN fails across most training trials due to the model being in a different part of state-space than it was trained on. LSR ESN and D2R2 both do better, with D2R2 being best overall. (Online version in colour.)