Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Boddupalli, Nibodh, Matchen, Timothy, Moehlis, Jeff
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2605.04337
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910194132320256
author Boddupalli, Nibodh
Matchen, Timothy
Moehlis, Jeff
author_facet Boddupalli, Nibodh
Matchen, Timothy
Moehlis, Jeff
contents Identifying governing equations for a dynamical system is a topic of critical interest across an array of disciplines, from mathematics to engineering to biology. Machine learning -- specifically deep learning -- techniques have shown their capabilities in approximating dynamics from data, but a shortcoming of traditional deep learning is that there is little insight into the underlying mapping beyond its numerical output for a given input. This limits their utility in analysis beyond simple prediction. Simultaneously, a number of strategies exist which identify models based on a fixed dictionary of basis functions, but most either require some intuition or insight about the system, or are susceptible to overfitting or a lack of parsimony. Here we present a novel approach that combines the flexibility and accuracy of deep learning approaches with the utility of symbolic solutions: a deep neural network that generates a symbolic expression for the governing equations. We first describe the architecture for our model, then show the accuracy of our algorithm across a range of classical dynamical systems.
format Preprint
id arxiv_https___arxiv_org_abs_2605_04337
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Symbolic Regression via Neural Networks
Boddupalli, Nibodh
Matchen, Timothy
Moehlis, Jeff
Dynamical Systems
Signal Processing
Machine Learning
Identifying governing equations for a dynamical system is a topic of critical interest across an array of disciplines, from mathematics to engineering to biology. Machine learning -- specifically deep learning -- techniques have shown their capabilities in approximating dynamics from data, but a shortcoming of traditional deep learning is that there is little insight into the underlying mapping beyond its numerical output for a given input. This limits their utility in analysis beyond simple prediction. Simultaneously, a number of strategies exist which identify models based on a fixed dictionary of basis functions, but most either require some intuition or insight about the system, or are susceptible to overfitting or a lack of parsimony. Here we present a novel approach that combines the flexibility and accuracy of deep learning approaches with the utility of symbolic solutions: a deep neural network that generates a symbolic expression for the governing equations. We first describe the architecture for our model, then show the accuracy of our algorithm across a range of classical dynamical systems.
title Symbolic Regression via Neural Networks
topic Dynamical Systems
Signal Processing
Machine Learning
url https://arxiv.org/abs/2605.04337