-
Example: https://mila.quebec/en/publications/
It would be nice to reuse the same code as in the Mila website. Not sure if that's 'easily' possible via RTD
-
Hi, I'm wondering whether the evaluation code of Linear Regression in Tables 10 & 12 of the paper can be provided. Thanks for your help!
-
Not sure if this is the right way to go about it so I'd like to ask what you all think... Would it make sense to make some adjoints for regularizers, and or attach them to specific layers?
ie:
```Ju…
-
When adding FC layer, BNN class adds copy of layer, according to
https://github.com/tianheyu927/mopo/blob/master/mopo/models/bnn.py#L141
Further, when copying a layer, the code uses repr funct…
-
As the 2010’s draw to a close, it’s worth taking a look back at the monumental progress that has been made in Deep Learning in this decade.
Tags: deep_learning
via Pocket https://ift.tt/…
-
Great work!
I am hoping if it would be possible to share the config for LLR. (Similar to the last section of readme.)
Also, I noticed you have learning rate configurations for CURE regularization …
-
Hi Yngve
I have been experimenting a bit with `LogisticGroupLasso` (for binary classification) and found it not to work super reliably, yet. `LogisticGroupLasso`, from what I have understood, is a …
-
While beginning to use Lipschitz regularization on CGSchNet models, I realized that in its current state, `lipschitz_projection()` is completely blind to `LinearLayer()` instances in a `SchnetFeature`…
-
There’s a line of work out of Michael Jordan’s lab regarding perturbed stochastic gradient descent that allegedly has advantages over SGD:
- Gradient Descent Can Take Exponential Time to Escape Sad…
-
arXiv论文跟踪