-
I am trying to run some evaluation but with the example scripts `scripts/infer/run_inference_with_python.py` I get different scores every time I run it.
My current hypothesis is that the weights of…
-
-
## Bug Description
We (@muelcm and I on separate inputs) have observed that steady state calculations restarted into transients exhibit non deterministic behaviors in the projection transfers. The in…
-
This might be very, very interesting: [Rapids Random Projections](https://rapidsai.github.io/projects/cuml/en/0.9.0/api.html#random-projections)
-
I'd like a signature along the lines of:
```r
step_randomproj(recipe, ..., dimensions, error)
```
where the user can either specify the number of dimensions to project into or an acceptable le…
-
**Problem description:**
My dataset cannot be represented as a `N_INSTANCES x N_DIMENSIONS` table of floats: the instances are rows from the main table in a relational database.
Thus, my custom …
-
Just pseudorandomly sign flip the data (and or randomly permute it) and run it through an (nlog(n)) Walsh Hadamard transform and the data takes on the Gaussian distribution.
If the data is very spars…
ghost updated
6 years ago
-
### Description of the problem
grdimage works fine for global grids that include the redundant 0 and 360 E longitudes. However, if you create a grid that doesn't include the redundant 360 E, the re…
-
Impressive work on the innovative data selection method!
I recently finished reading your paper. I'm particularly curious about the computation of the gradient projection. In your paper, you mention…
-
There are several Win32 APIs that take callbacks, e.g. WNDPROCs or DLGPROCs. These are currently projected as delegates, and if you do the "natural thing" and assign static methods to fields of these …