-
### Motivation and description
Is there such a thing as too many activation functions? I haven't decided on which of these, or if all:
**Natural Logarithm rescaled ReLU (NLReLU)**
https://arxiv…
-
I found this work really fascinating and I was wondering if you could provide code for computing the gold standard? I tried computing it using pysaliency but I must be doing something wrong because it…
-
Are there any plans to support DirectML as an alternative to TF?
Have not seen this request in the Issues list.
-
Thank you for sharing, these functions seem very useful to me. But could you provide some examples or a guide so that others can actually run this code? Just having the kernel function definitions mak…
-
## Keyword: out of distribution detection
There is no result
## Keyword: out-of-distribution detection
There is no result
## Keyword: expected calibration error
There is no result
## Keyword: overc…
-
Hey,
I compared pyroomacoustics with habets image method RIR generation code and was confused by two things:
- attenuation
- time of flight
2. big netwo…
-
Hi. I am trying to build the Apple Watch dataset that can be fed into the DNNs. I guess the path to create the dataset (is this correct?) is to:
- Run the preprocessing_runner.py at (https://githu…
-
Some thoughts on the Model interface below. I'd like to hear what others think.
### Instance equivalence tests
##### Dealing with inheritance
As I was rewriting `Model.__eq__()` to handle self-refere…
-
In GitLab by @corepointer on Mar 18, 2022, 11:31
We have most of our neural network operators (convolutions et al) implemented as calls to
cuDNN. An initial (pooling) operator is ported from SystemDS…