NTK4A
Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture" (by thegregyang)
GP4A
Code for NeurIPS 2019 paper: "Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes" (by thegregyang)
NTK4A | GP4A | |
---|---|---|
2 | 3 | |
90 | 231 | |
- | - | |
10.0 | 10.0 | |
almost 4 years ago | almost 4 years ago | |
Jupyter Notebook | Jupyter Notebook | |
- | - |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
NTK4A
Posts with mentions or reviews of NTK4A.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-01-07.
-
[D] What is currently the best theoretical book (or notes) about Convolutional Neural Networks?
The relationship to Gaussian processes is also important. See https://arxiv.org/abs/2006.14548 and the other papers on that topic
-
[R] Greg Yang's work on a rigorous mathematical theory for neural networks
Found relevant code at https://github.com/thegregyang/NTK4A + all code implementations here
GP4A
Posts with mentions or reviews of GP4A.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-01-07.
-
[N] Getty Images is suing the creators of AI art tool Stable Diffusion for scraping its content
Greg Yang's mathematical theory behind NNs is a better introduction. He also introduces tensor programs as a way to talk about arbitrary NNs (operating on Rn though in contrast to Float). Might be interesting to you as well :)
-
[R] Greg Yang's work on a rigorous mathematical theory for neural networks
took a quick glance (https://arxiv.org/abs/1910.12478 and https://proceedings.mlr.press/v139/yang21c.html), a few theorems but where r the proofs?
What are some alternatives?
When comparing NTK4A and GP4A you can also consider the following projects:
mup - maximal update parametrization (µP)