BriefGPT.xyz
Dec, 2018
贝叶斯层：神经网络不确定性模块
Bayesian Layers: A Module for Neural Network Uncertainty
HTML
PDF
Dustin Tran, Dusenberry Mike, Mark van der Wilk, Danijar Hafner
TL;DR
Bayesian Layers是一种用于神经网络不确定性快速实验的模块，能够通过确定性和随机函数的统一抽象进行组合，从而实现可伸缩性，并且能够捕获权重、激活和功能本身等方面的不确定性，同时支持反向传递不确定性，同时提供了代码示例，可用于Edward2概率编程语言中的概率程序。
Abstract
We describe
bayesian layers
, a module designed for fast experimentation with
neural network uncertainty
. It extends neural network libraries with layers capturing uncertainty over weights (Bayesian neural nets),
→