Chaotic Systems and Neural Networks

Published: 02 Jun 2024, Last Modified: 27 Apr 2024Selected for a Talk @ Advances in Data Science and Artificial Intelligence (ADSAI) Conference 2024EveryoneCC BY 4.0
Abstract: In this note we demonstrate that relatively simple neural net losses can be trained to do forecasting on standard discrete-time chaotic dynamical systems such that topological invariants estimated from the neural predictions are close to the ground--truth.
Loading