BriefGPT.xyz
Sep, 2019
神经切向核的有限深度和宽度修正
Finite Depth and Width Corrections to the Neural Tangent Kernel
HTML
PDF
Boris Hanin, Mihai Nica
TL;DR
我们证明了在具有有限深度和宽度的随机初始化的ReLU网络中，神经切向核（NTK）的平均值和方差的精确缩放。
Abstract
We prove the precise scaling, at finite
depth
and
width
, for the mean and variance of the
neural tangent kernel
(NTK) in a
→