BriefGPT.xyz
Feb, 2017
从生成模型学习分层特征
Learning Hierarchical Features from Generative Models
HTML
PDF
Shengjia Zhao, Jiaming Song, Stefano Ermon
TL;DR
本文证明已有的变分方法无法很好地训练分层潜变量模型, 并且提出了一种不依赖先前知识、能够在多个自然图像数据集上学习高度可解释和分解分层特征的替代架构。
Abstract
deep neural networks
have been shown to be very successful at learning feature hierarchies in
supervised learning
tasks.
generative models
→