-
At first, thank you a lot for your contributions. They are very valuable to improve my understanding of the original paper.
I have a fundamental question regarding the implementation of the [Neural…
-
Hello, I've been seeing loss_weights used in quite a lot of codes and examples, and as far as I can deduce it just multiplies the loss with the specified number ? Obviously I'm wrong but can anyone gi…
-
Hi
I am new to JAX, and my question is can we use this package to train regular neural networks without the NTK notion? If this is the case, are there any examples or a document to start with?
T…
-
### 检查清单
- [X] 合法的、无木马植入的站点。
- [X] 有实质性原创内容的 HTTPS 站点,发布过至少 5 篇原创文章,内容题材不限。
- [X] 有独立域名,非免费域名。
### 站点信息
```json
{
"title": "Lil'Log",
"url": "https://lilianweng.github.io/",
"avatar…
-
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
-
Translate https://github.com/amzn/xfer/tree/master/finite_ntk to JAX.
Use https://github.com/google/neural-tangents for the NTK kernel, and https://github.com/dfm/tinygp for the GP code.
-
Thank you very much for this excellent library and your research, both are highly useful!
Tancik et al. [1, Remark below Eqn. (2)] and Jacot et al. [2, Proof of Proposition 2] both mention that the…
-
Hi, nice work! You expanded and delved the work [Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel](https://arxiv.…
-
Hi, thanks for your excellent codebase. I am trying to train a (finite-width) linearized vision transformer (which I have obtained from the [vision_transformer](https://github.com/google-research/visi…
-
Hey, thanks for the great work!
I'm using BatchNorm in my network, but have set the `use_running_average` parameter of BatchNorm layers to true, which means it will not compute any running mean/std…