-
**Paper**: Local Competition and Stochasticity for Adversarial Robustness in Deep Learning (http://proceedings.mlr.press/v130/panousis21a)
**Venue**: International Conference on Artificial Intellig…
-
I am just trying to test out training my first model and it appears to use CPU training instead of GPU training despite detecting and gpu and saying it is initializing it. nvidia-smi show that no proc…
-
Hello,
I'm investigating a potential use of Juice framework for deep reinforcement learning (I'm also learning the RL and deep learning as I go, so apologies for potentially newbie questions). RL r…
hweom updated
2 years ago
-
plone.scale increases the file size of images of type PNG.
test https://github.com/mamico/plone.scale/commit/0b6c36f40039cad40de27744c70bbab726a3d517
-
 Codeium Blackbox and tabnine have in line code suggestions and Blockman has no awareness of…
-
Hello,
I am calculating the EK-FAC representation on the linear layers of a model with an embedding layer. The inputs are integers which are lookup values and therefore should not be differentiated…
Xuzzo updated
2 weeks ago
-
Hi Korbinian,
Moving the dialog here....the clear SWI portion of things is all resolved. I've moved the newer ROMEO & Laplacian unwrapping stuff here, so you can close the SWI part at your leisure.…
-
I did a bit of research on environments, closures, lambda lifting, etc. etc. for Myia and thought I would write a quick summary. I'll go over some basic definitions to ground the discussion, even thou…
-
Is there any way to use autodiff on sparse scipy matrices? The docs say `np.dot` isn't supported (and attempting it throws a `ValueError: setting an array element with a sequence.`). I can get the dot…
-
Hi,
I am working on the algorithms of natural gradient descent and ansatz-based imaginary time evolution, in which I want to calculate the hessian with respect to parameters in a forward-reverse hybr…