-
In 0.6 calls like `1./f` no longer fall back to `1/f`, as it is broadcasted, and hence currently uses the constructor with the domain of `f`, regardless of the singularities introduced.
Apart fr…
-
"Warp uses a source-code transformation approach to auto-differentiation."
I don't quite understand what this means and I know this is not how one is supposed to use tape but my question is: Is it …
jc211 updated
11 months ago
-
@schornakj found documentation on [`ceres` local parameterization](http://ceres-solver.org/nnls_modeling.html#localparameterization) that can help with the over-parameterization of optimization proble…
-
Get and return a user's Soundhound/Shazam tagged tracks as part of their recent tracks. Results should be in a mixed list based on when they were scrobbled/tagged, and have a "type" property for the a…
-
I am working on a project that utilizes Chebyshev polynomials and might use other types of polynomials in the future, and I would like to leverage jit and auto differentiation through JAX. numpy suppo…
-
## 🚀 Feature
Hello, I'm using kornia to work with MRI images for the auto-differentiation feature but out of the deep-learning context. It came super usefull to not re-implement every thing.
So I…
-
The following docs from AutoValue and Immutables seem to indicate that both libraries do not recommend using the JavaBeans-style property accessors (`getProperty()`, `isBoolean()`, etc)
https://githu…
-
### Feature details
Currently, `SpecialUnitary` supports broadcasting and is auto-differentiable when it is broadcasted.
In addition #3674 adds differentiation with transforms to `SpecialUnitary`.…
-
The operation that I'm trying to do is take a five-component vector whose entries correspond to the degrees of freedom in a 3x3 traceless, symmetric tensor then find a rotation matrix whose columns ar…
-
It would be good if this library implemented the iterator:
https://github.com/JuliaDiffEq/ArrayInterface.jl#findstructralnzx
This would allow it to be used as a sparsity type in SparseDiffTools.…