Dissecting Neural ODEs
read the original abstract
Continuous deep learning architectures have recently re-emerged as Neural Ordinary Differential Equations (Neural ODEs). This infinite-depth approach theoretically bridges the gap between deep learning and dynamical systems, offering a novel perspective. However, deciphering the inner working of these models is still an open challenge, as most applications apply them as generic black-box modules. In this work we "open the box", further developing the continuous-depth formulation with the aim of clarifying the influence of several design choices on the underlying dynamics.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
When does dissipation help neural surrogates learn open quantum dynamics?
Dissipation enhances neural surrogate learnability of open quantum dynamics in spin chains at intermediate sizes via contraction, but fidelity metrics must separate genuine dynamics from steady-state trivialization.
-
Frequency-Domain Neural ODEs for Modeling Non-Linear Dynamical Systems
FNODE projects Neural ODE dynamics into the frequency domain via FFT and reports better generalization and convergence stability than GRUs, LSTMs, and ANODE on Lotka-Volterra, forced Duffing, Van der Pol, and Lorenz systems.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.