An Introduction to Variational Autoencoders

被引：1470

作者：

Kingma, Diederik P. ^{[1
]}

Welling, Max ^{[2
,3
]}

机构：

[1] Google, Mountain View, CA 94043 USA

[2] Univ Amsterdam, Amsterdam, Netherlands

[3] Qualcomm, San Diego, CA USA

来源：

FOUNDATIONS AND TRENDS IN MACHINE LEARNING | 2019年 / 12卷 / 04期

关键词：

GRADIENT; LIKELIHOOD; ALGORITHMS; MODELS;

D O I：

10.1561/2200000056

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Variational autoencoders provide a principled framework for learning deep latent-variable models and corresponding inference models. In this work, we provide an introduction to variational autoencoders and some important extensions.

引用

页码：4 / 89

页数：86

共 139 条

[71]

Heess N, 2015, ADV NEUR IN, V28

[72]

Hernandez-Lobato Jose Miguel., 2016, Black-box alpha-divergence minimization

[73]

Higgins I., 2017, INT C LEARNING REPRE, V2, P1

[74] THE WAKE-SLEEP ALGORITHM FOR UNSUPERVISED NEURAL NETWORKS [J].

HINTON, GE ;

DAYAN, P ;

FREY, BJ ;

NEAL, RM .

SCIENCE, 1995, 268 (5214) :1158-1161

[75]

Hochreiter S, 1997, Neural Computation, V9, P1735

[76]

Hoffman M. D., 2016, NEURIPS WORKSH

[77]

Hoffman MD, 2013, J MACH LEARN RES, V14, P1303

[78]

Houthooft Rein, 2016, Advances in Neural Information Processing Systems, V29

[79]

Jang E., 2017, INT C LEARN REPRESEN

[80]

Johnson MJ, 2016, ADV NEUR IN, V29

← 3 4 5 6 7 8 9 10 11 12 →