-
I’m trying to use the DiffEqFlux package to define a machine learning model for an ODE. The model I need is a Neural ODE whose input is the initial condition and a continuos time signal.
![formula…
-
tried working through the basic supervised example, and getting a really strange error related to the output from the NNODE layer. Pretty peculiar, when the model is called from Flux the data disappea…
-
Hello - thanks for this resource! I find it really helpful.
I've been meaning to ask if it would be acceptable to add a reference to our recent paper https://arxiv.org/abs/2005.08926. I'm happy to …
-
If we are lucky enough to beat existing methods with current brute-force optimization, we can go further to explore deep deformation functions for better convergence.
-
Hello, first of all, thanks for this package is very useful
I'm new in the scientific machine learning field and currently, I'm learning, and very interested, in the UDEs to model physical systems.…
-
**Describe the bug**
While using DiffEqFlux, Flux, and CuArrays, I got the following error message.
```
*** Error in `julia': double free or corruption (out): 0x00007ffee6bd8d00 ***
======= Back…
-
Thanks for your list of neuralode papers, I'm also working on using deep learning to approximate dynamic systems. I'm writing this email to introduce my recent work
Our work starts from bidging dee…
-
I am trying to run and understand 2.Demo_optimize_bullet_trajectory.ipynb in seminars/2019-03-Neural-Ordinary-Differential-Equations but when I arrive at the line where you want to import a few things…
-
I'm upgrading my neural ODE setups to use DiffEqFlux v1.1.1 (updating from `neural_ode` to `NeuralODE`) but I noticed that my neural ODEs don't train anymore, i.e. `Flux.train!` does not change the we…
-
_update_: **The crux:** found the single line change that converts this from working to non-working!!! **This is not the fix-- it just pinpoints what makes Zygote fail.**
The batch of k items to…
cems2 updated
4 years ago