-
I am trying to jaxopt.Bisection to replace the use of scipy.optimize.bisect in a computational model but Bisection hangs when I run my code.
The basic structure includes 2 functions that are both …
-
Dear Dr. Pan @pswpswpsw ,
My system has a simple nonlinear sine function. The hyperparam selection figure is as follows so that I choose rank=90 and sigma=4. But the reconstruction error plot lo…
-
The tutorial code for multiple shooting (https://diffeqflux.sciml.ai/dev/examples/multiple_shooting/) doesn't work for me. First, the second line
`using DiffEqFlux: group_ranges`
gives an error: `ER…
-
I got some luck to find that `jax.nn.sigmoid` was causing a very vague error for the last two days. The following code may reproduce this problem:
```python
from functools import partial
import t…
-
>WARNING: replacing module Delhi.
WARNING: replacing module Delhi.
┌ Info: Fitting model...
└ @ Main In[8]:49
>ArgumentError: "/home/ayush/julia_ode/neural-ode-weather-forecast/scripts/data/**Da…
-
Hello,
I'm not sure if this is a feature request, or perhaps a documentation request, or maybe me just not understanding how things work. In the test and example for the neural ode with mass matri…
-
I am trying to use `DiffEqFlux`. However, when loading this package the following warning is raised:
```juliacli
julia> using DiffEqFlux
┌ Warning: Error requiring `Flux` from `GalacticOptim`
│ …
-
I think the docs should have these sections:
1. Neural networks can be defined where the "activations" are nonlinear functions described by differential equations
2. Neural networks can be defined…
-
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…
-
I was trying to set up a sequential learning problem as follows:
```
using Flux, DiffEqFlux
using DifferentialEquations
using Random
ndata= 11;
tspan = (0.0f0, 1.0f0);
tdata = range(tspan[1],…