Greg Yang

Code for NeurIPS 2019 paper: "Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes"

thegregyang

Loss and accuracy go opposite ways...right?

thegregyang

Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"

thegregyang

Computing the eigenvalues of Neural Tangent Kernel and Conjugate Kernel (aka NNGP kernel) over the boolean cube

thegregyang