Neural ODEs - Theory and Application: From Residual Networks to Continuous-Depth Dynamics

A Neural Ordinary Differential Equation (Neural ODE) uses a neural network to represent a system’s rate of change. This project investigates how well such a model can learn logistic growth from samples of a single solution. We first derive the exact solution using the Bernoulli substitution, then use it to generate 100 noise-free training points. A small neural network represents the growth rate, and a fourth-order Runge–Kutta solver produces the predicted population. In the reference run, the learned trajectory has a root-mean-square error of approximately 0.20 population units over the training points, but eventually exceeds the true carrying capacity. The same overshoot occurs in ten runs with different random initializations. Examining the learned growth rate shows that the models do not recover the equilibrium at the carrying capacity. For this experiment, agreement with the observed growth curve does not guarantee agreement with the system’s long-term behavior.

Authors

Institutions

Publication Details

Journal
Valency Hub
Published
2026-11-13
DOI
https://doi.org/10.83295/8pvm-8ux2
Primary Topic
Model Reduction and Neural Networks
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Neural ODEs - Theory and Application: From Residual Networks to Continuous-Depth Dynamics

Sebastian Chegini
Valency Hub
Model Reduction and Neural Networks
preprint

Neural ODEs - Theory and Application: From Residual Networks to Continuous-Depth Dynamics

Sebastian Chegini
preprint en

Abstract

A Neural Ordinary Differential Equation (Neural ODE) uses a neural network to represent a system’s rate of change. This project investigates how well such a model can learn logistic growth from samples of a single solution. We first derive the exact solution using the Bernoulli substitution, then use it to generate 100 noise-free training points. A small neural network represents the growth rate, and a fourth-order Runge–Kutta solver produces the predicted population. In the reference run, the learned trajectory has a root-mean-square error of approximately 0.20 population units over the training points, but eventually exceeds the true carrying capacity. The same overshoot occurs in ten runs with different random initializations. Examining the learned growth rate shows that the models do not recover the equilibrium at the carrying capacity. For this experiment, agreement with the observed growth curve does not guarantee agreement with the system’s long-term behavior.

Valency Hub
Foothill College (US)
Model Reduction and Neural Networks
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon