Back to search

Georgia Institute of Technology

Can a Neural ODE learn a Chaotic System?

Abstract

dc:description.abstract

Learning chaotic dynamical systems from data presents significant challenges due to their inherent unpredictability and high sensitivity to initial conditions. Conventional metrics of model performance, such as generalization error, often fail to capture a neural network's ability to reproduce the invariant statistics of these complex systems. In this thesis, we demonstrate through a comprehensive set of examples that pointwise accuracy (measured through generalization error) does not necessarily translate into statistical fidelity. Our evaluation leverages concepts from ergodic theory to provide a more nuanced assessment of model performance. Then, we propose and implement modifications to the training scheme by incorporating Jacobian information. We show that this approach enables the reproduction of correct physical measures for chaotic systems, which we term "statistically-accurate learning.'' We also report the failure mode of our proposed training scheme and give a theoretical explanation with shadowing lemma. Our work offers valuable insights into the limitations of traditional machine learning theory when applied to complex systems. These findings have implications for improving the reliability and interpretability of machine learning models in complex dynamical contexts, with potential applications in fields such as climate modeling, fluid dynamics, and nonlinear control systems.

Degree

thesis:*
Level thesis:degree_level
Masters
Department dc:contributor.department
Computational Science and Engineering
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Park, Jeongjin
Advisors dc:contributor.advisor
  • Chandramoorthy, Nisha
  • Chen, Peng
Committee member dc:contributor.committeemember
  • Qian, Elizabeth

Subjects

dc:subject × 4

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1853/75730

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Park, Jeongjin. Can a Neural ODE learn a Chaotic System?. Masters thesis, Georgia Institute of Technology, 2024. https://hdl.handle.net/1853/75730