-
With a bit of work, `ReverseDiff` should be possible to support for all the distributions here. The idea is to:
1. Use forward-mode differentiation for univariate distributions, for some of which we …
-
**Is your feature request related to a problem? Please describe.**
The Random method (https://docs.microsoft.com/en-us/qsharp/api/qsharp/microsoft.quantum.intrinsic.random) is described as an operati…
-
Hi, I'm trying to train the UniversalODE model of the predator-prey example but sciml_train fails (apparently caused by Zygote.gradient)
```
using DiffEqFlux, Flux, Optim, OrdinaryDiffEq, CUDA, Di…
-
```
## Classification of MNIST dataset
## with the convolutional neural network known as LeNet5.
## This script also combines various
## packages from the Julia ecosystem with Flux.
using Flux
…
-
SIRF-exercises registration demo does
```python
resampler = Reg.NiftyResample()
resampler.set_reference_image(ref)
resampler.set_floating_image(flo)
resampler.add_transformation(tm)
resampler.se…
-
## Description
Use the RAII idiom to make sure that nested autodiff is always properly deinitialized. More thorough discussion at
https://discourse.mc-stan.org/t/proposal-raii-for-nested-autodiff/1…
-
Here is a MWE :
```julia
using KernelFunctions, Zygote
A = KernelFunctions.ColVecs(rand(10, 10))
t = ScaleTransform(rand())
typeof(map(t, A)) # ColVecs
v, g = pullback(map, t, A)
typeof(v) # Ve…
-
Today I discovered that Zygote.jl lists FFTW.jl as a dependency. FFTW.jl, in turn, depends on FFTW_jll and MKL_jll (the two available backends).
* MKL_jll comes with artifacts that weigh in around a …
Byrth updated
4 years ago
-
I know that the adjoint source is defined as the derivative of objective function with respect to the electric field. If the objective function is defined as the square of a (a is mode coefficient), t…
-
Although I am minimizing my objective function, its value appears to rise in some designs while running a shape optimization. I look at my objective function value from the history_project.dat file.
…