BriefGPT.xyz
May, 2023
神经网络作为无限树状概率图模型
On Neural Networks as Infinite Tree-Structured Probabilistic Graphical Models
HTML
PDF
Boyao Li, Alexandar J. Thomson, Matthew M. Engelhard, David Page
TL;DR
本文提出了一种创新性的解决方案，通过构建无限树状PGMs来精确对应神经网络，发现DNNs在前向传播过程中实际上是精确的PGM推理的近似，这种直接的近似揭示了DNNs的精神内核。
Abstract
deep neural networks
(DNNs) lack the precise semantics and definitive probabilistic interpretation of
probabilistic graphical models
(PGMs). In this paper, we propose an innovative solution by constructing
→