-
Hi,
Thank you for sharing this great library. I have two questions which are relevant to each other:
1. For `nngp`, we are assuming that the number of neurons goes to infinity. Why do you need t…
-
arXiv论文跟踪
-
Hi!
A bug seems to occur when I was trying to evaluate analytic NTKs using sparse input data -- the evaluated kernel contains `nan` entries. This can be reproduced with the following lines of code…
-
Thanks for making this great resource available!
I wonder if the layers (such as `Conv` and `Dense`) in `stax` can be specified to be non-trainable? If not, is there a way of modifying the output …
-
Thanks a lot for making this repository public!
When running the notebooks [`weight_space_linearization.ipynb`](https://github.com/google/neural-tangents/blob/master/notebooks/weight_space_lineari…
-
-
I'm starting this as a catch-all for discussion about concepts that heavily overlap between disciplines. I had started to contemplate how to merge the implementation that you're developing here with …
-
I would like to obtain the activation of every SOM unit for a given input, i.e., not just the MAU/BMU.
I see from the comment here https://github.com/peterwittek/somoclu/issues/39#issuecomment-23597…