-
https://arxiv.org/pdf/2005.04849.pdf
This looks like what we are attemting to do at https://github.com/SciML/DataDrivenDiffEq.jl/issues/54
They claim `intrepretability` like SINDy and yet the fra…
-
Hi , using following packages
```julia
[b0b7db55] ComponentArrays v0.8.19
[aae7a2af] DiffEqFlux v1.34.0
[587475ba] Flux v0.11.6
[429524aa] Optim v1.2.4
```
the example of NeuralODE us…
-
```Julia
using DiffEqFlux, OrdinaryDiffEq, Flux, Optim, Plots
using Flux: gradient
using Flux.Optimise: update!
using Random
n_plot = 10
n_epoch = 100000
n_exp = 30
function trueODEfunc(dy…
-
In https://arxiv.org/abs/2005.13420 Onken and Ruthotto conclude using some of the examples in DiffEqFlux that Disc-Opt methods can achieve similar performance to Opt-Disc at inference with drastically…
-
Hi, I experience following error while trying to setup the project
```
Traceback (most recent call last):
File "run-mujoco.py", line 55, in
main()
File "run-mujoco.py", line 50, in mai…
-
Hi
I’m new with Julia and I have some problems with the creation of a multilayer perceptron.
I’ve tried following some guides about this topic but I couldn’t figure it out the solution.
My question…
-
What should be the best way to fix this? @jiweiqi
-
Not specifying the solver for `DiffEqFlux.NeuralODE` makes the solver default to a CompositeAlgorithm with (Tsit5, Rosenbrock23). When testing the stiffness `derivative_utils.calc_J!` is invoked which…
-
Right now, this works ( very slow )
```julia
using DiffEqFlux, OrdinaryDiffEq, Flux, Optim, Plots
using DataDrivenDiffEq, ModelingToolkit
using Zygote
u0 = Float32[2.; 0.]
datasize = 30
ts…
-
## Code
```Julia
using OrdinaryDiffEq, Flux, Optim, Random, Plots
using DiffEqSensitivity
using Zygote
using ForwardDiff
using LinearAlgebra, Statistics
using ProgressBars, Printf
using Flux.O…