BriefGPT.xyz
Oct, 2023
使用联合潜在空间能量先验学习层次特征
Learning Hierarchical Features with Joint Latent Space Energy-Based Prior
HTML
PDF
Jiali Cui, Ying Nian Wu, Tian Han
TL;DR
本文研究多层生成模型在学习分层表示中的基本问题,并提出了一种联合潜在空间的基于能量的模型,通过多层潜在变量实现了有效的分层表示学习,并对数据分布建模。
Abstract
This paper studies the fundamental problem of
multi-layer generator models
in learning
hierarchical representations
. The multi-layer generator model that consists of multiple layers of
→