-
Hi there,
Congratulations on your paper "Towards Adaptive Residual Network Training: A Neural-ODE Perspective"!
Seems like in the code, the default setting is not optimal (for example, it uses c…
-
Hi,
I adapted the example neural ode code at https://diffeqflux.sciml.ai/dev/examples/neural_ode_flux/ to stiff ode problem of [Robertson's problem](https://docs.sciml.ai/latest/tutorials/advanced_…
-
Trying to run the ANODE [example in the docs](https://diffeqflux.sciml.ai/dev/examples/augmented_neural_ode/) on the GPU by moving
`data`, `labels`, `model`, and `parameters` to GPU using the `gpu` …
-
Q. Is it okay to integrate the dynamics using ode45, which may cause deviations from the SO(3)?
#Ref.
https://github.com/fdcl-gwu/decoupled-yaw-controller-comparison/blob/1d067d5339546a3bc106daae…
-
https://github.com/ChrisRackauckas/universal_differential_equations/issues/31 it's not hard but if someone asks a questions it means we're not clear enough.
-
Hi all,
I am trying to use DEQ models to fit 1 toy data point by wrapping the neural net in a SteadyStateProblem. However, when I run a piece of code like this
```
using Flux
using DiffEqSensi…
-
Suggested by @AlexAndorra [here](https://github.com/pymc-devs/pymc3/pull/4088#issuecomment-690479838), opening this as a placeholder so I don't forget.
Any preferences on `black` formatting, or are…
-
In "An Introduction to modeling neural dynamics" by Borgers, section 20.2, the synaptic current is defined as:
```
I_syn = g_bar_syn * s(t) (V_rev - V_post)
dq/dt = (1+tanh(V/10)) / 2 * (1-q) / tau…
-
It would be good to take https://gist.github.com/jonniedie/55bc9bee2fe9a91c28bb6623e7afc00b all of the way to a comparison of https://github.com/rtqichen/torchdiffeq/blob/master/examples/ode_demo.py f…
-
Hi, thanks for the awesome package! Unfortunately I'm having issues using it for my work. I basically want to integrate a set of equations of motions defined by a Hamiltonian `H(p, x)` that is too com…