-
Currently FMI 2.0 provides and interface to provide partial derivatives in the form of dirctional derivatives (e.g., Jacobian J times direction vector v, Jv)
For several use cases, it would be ben…
-
I was wondering whether there is interest in someone (me?) implementing operations under which block-matrices are potentially closed (i.e. perhaps return another block-matrix), such as multiplication,…
-
Looking through [`neural_de.jl`](https://github.com/JuliaDiffEq/DiffEqFlux.jl/blob/master/src/neural_de.jl) it doesn't look like it'll be hard to implement a `NeuralDAE`.
I'm interested in using th…
-
In an attempt to create a bilinear upsampling layer in Flux like [pythorch's Upsample](https://pytorch.org/docs/stable/nn.html#upsample), I wrote some code using [`Interpolations.jl`](https://github.c…
-
Hi @baggepinnen,
I came across this paper today https://arxiv.org/abs/1905.12893, and thought it was quite nice; it seemed like a sensible framework for introducing regularization similar to your `…
-
The current design requires that rules have the form
```julia
function rrule(::typeof(foo), args...)
...
return (rule_arg_1, rule_arg_2, ...)
end
```
I would like to propose to extend…
-
Document why certain sections are deprecated, as described in this set of email messages.
On Saturday, January 11, 2020 at 1:33:13 PM UTC-5, Jon P wrote:
Quick question: Why are the following sect…
-
Building it fails at the first CPU operator with `Undefined buffer calling const method dimensions` -- unfortunately this app isn't in the regular set of tested apps currently, as it requires stuff no…
-
In a NeuralODE problem I am testing two trivial models
```
model1 = FastDense(2,2)
model2 = FastChain(model1)
```
I believe these are nominally identical models. Yet when called in a batch mode,…
cems2 updated
4 years ago
-
I get a reshape error when evaluation the generated model because the code assumes the size of the input variables to be (1,2) in line 35 of SVMSurrogate.jl
```
function (svmsurr::SVMSurrogate)(va…