English

Neural Networks for Lorenz Map Prediction: A Trip Through Time

Machine Learning 2020-11-17 v5 Machine Learning

Abstract

In this article the Lorenz dynamical system is revived and revisited and the current state of the art results for one step ahead forecasting for the Lorenz trajectories are published. Multitask learning is shown to help learning the hard to learn z trajectory. The article is a reflection upon the evolution of neural networks with respect to the prediction performance on this canonical task.

Keywords

Cite

@article{arxiv.1903.07768,
  title  = {Neural Networks for Lorenz Map Prediction: A Trip Through Time},
  author = {Denisa Roberts},
  journal= {arXiv preprint arXiv:1903.07768},
  year   = {2020}
}

Comments

Technical Report

R2 v1 2026-06-23T08:12:17.110Z