I slightly changed a NeuralODE layer and added a few new weights parameters, but it can’t fit the simple data and show the warning ┌ Warning: dt <= dtmin. Aborting. There is either an error in your model specification or the true solution is unstable. └ @ SciMLBase /home/solar/.julia/packages/SciM…

Custom NeuralODE layer trains innefficiently

Sunny June 4, 2021, 3:13pm 3

Nope, I created the issue

Topic		Replies	Views
Using Neural ODEs to learn a family of ODEs (with Automatic Differentiation) Machine Learning question , zygote , sciml , autodiff , lux	13	307	December 9, 2025
NeuralODE training failed on GPU with Enzyme Machine Learning ode , enzyme	6	184	August 25, 2024
All Adjoint Methods Fail on Simple Neural ODE Example General Usage	7	299	July 22, 2023
Parameter tuning in neural ODE Machine Learning diffeq , flux	15	2109	July 21, 2019
Neural ODE in DiffEqFlux that is not a time series Machine Learning diffeq	6	1464	March 30, 2019