An Improved Autoencoder Conjugacy Network to Learn Chaotic Maps
Dynamical Systems
2025-07-15 v1
Abstract
We introduce a method for learning chaotic maps using an improved autoencoder neural network that incorporates a conjugacy layer in the latent space. The added conjugacy layer transforms nonlinear maps into a simple piecewise linear map (the tent map) whilst enforcing dynamical principles of well-known and defective conjugacy functions that increase the accuracy and stability of the learned solution. We demonstrate the method's effectiveness on both continuous and piecewise chaotic one-dimensional maps and numerically illustrate improved performance over related traditional and recently emerged deep learning architectures.
Keywords
Cite
@article{arxiv.2507.09835,
title = {An Improved Autoencoder Conjugacy Network to Learn Chaotic Maps},
author = {Meagan Carney and Cecilia González-Tokman and Ruethaichanok Kardkasem and Hongkun Zhang},
journal= {arXiv preprint arXiv:2507.09835},
year = {2025}
}
Comments
25 pages, 11 figures