BriefGPT.xyz
Dec, 2018
一种新颖的变分自编码器及其在生成建模、分类和序数回归中的应用
A Novel Variational Autoencoder with Applications to Generative Modelling, Classification, and Ordinal Regression
HTML
PDF
Joel Jaskari, Jyri J. Kivinen
TL;DR
文中提出了一种新的基于变分自编码器的概率生成模型，该模型使用新颖的方法确定潜在变量先验和强制序数单位，并用于有监督、无监督和半监督学习以及标称和序数分类，实验结果表明该模型在这两方面的分类任务中表现较优。
Abstract
We develop a novel
probabilistic generative model
based on the
variational autoencoder
approach. Notable aspects of our architecture are: a novel way of specifying the latent variables prior, and the introduction
→