thegregyang
Mathematician and AI researcher @ xAI. Morgan Prize Honorable Mention 2018.
Microsoft Research AI
Pinned Repositories
mup
maximal update parametrization (µP)
azure-docs
Open source documentation of Microsoft Azure
dfa-scales-to-modern-deep-learning
Study on the applicability of Direct Feedback Alignment to neural view synthesis, recommender systems, geometric learning, and natural language processing.
GP4A
Code for NeurIPS 2019 paper: "Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes"
LaTeX-Workshop-wiki
Public repo for contributing to https://github.com/James-Yu/LaTeX-Workshop/wiki
LossUpAccUp
Loss and accuracy go opposite ways...right?
neural-tangents
Fast and Easy Infinite Neural Networks in Python
NNspectra
Computing the eigenvalues of Neural Tangent Kernel and Conjugate Kernel (aka NNGP kernel) over the boolean cube
NTK4A
Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
thegregyang's Repositories
thegregyang/GP4A
Code for NeurIPS 2019 paper: "Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes"
thegregyang/NTK4A
Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"
thegregyang/LossUpAccUp
Loss and accuracy go opposite ways...right?
thegregyang/NNspectra
Computing the eigenvalues of Neural Tangent Kernel and Conjugate Kernel (aka NNGP kernel) over the boolean cube
thegregyang/neural-tangents
Fast and Easy Infinite Neural Networks in Python
thegregyang/dfa-scales-to-modern-deep-learning
Study on the applicability of Direct Feedback Alignment to neural view synthesis, recommender systems, geometric learning, and natural language processing.
thegregyang/azure-docs
Open source documentation of Microsoft Azure
thegregyang/LaTeX-Workshop-wiki
Public repo for contributing to https://github.com/James-Yu/LaTeX-Workshop/wiki
thegregyang/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
thegregyang/pytorch-meta
A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch
thegregyang/transformers
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.