A neural network is trained to generate symbolic expressions for the governing equations of dynamical systems, with accuracy demonstrated on classical examples.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Ideal RfR models reconstruct the original chaotic attractor geometry as a time-delay embedding by matching positive and negative Lyapunov exponents and their vectors.
citing papers explorer
-
Symbolic Regression via Neural Networks
A neural network is trained to generate symbolic expressions for the governing equations of dynamical systems, with accuracy demonstrated on classical examples.
-
Geometric structure of ideal data-driven dynamical model using RfR method
Ideal RfR models reconstruct the original chaotic attractor geometry as a time-delay embedding by matching positive and negative Lyapunov exponents and their vectors.