BriefGPT.xyz
Aug, 2019
神经网络高斯过程的有限尺寸修正
Finite size corrections for neural network Gaussian processes
HTML
PDF
Joseph M. Antognini
TL;DR
研究使用高斯过程模拟神经网络的兴趣越来越浓厚，本研究针对具有单隐藏层的大规模有限完全连接网络展示了输出在初始化时的高斯分布，同时发现该扰动的尺度与神经网络单元的数量成反比例关系，高阶项逐渐衰减，进而回复到Edgeworth扩展的形式；最后观察到理解该扰动在训练期间如何改变，将有助于展示高斯过程框架在模拟神经网络行为时的适用范围。
Abstract
There has been a recent surge of interest in modeling
neural networks
(NNs) as
gaussian processes
. In the limit of a NN of infinite width the NN becomes equivalent to a Gaussian process. Here we demonstrate that
→