An Introduction to Variational Autoencoders

被引:1284
|
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
收藏
页码:4 / 89
页数:86
相关论文
共 50 条
  • [1] Tree Variational Autoencoders
    Manduchi, Laura
    Vandenhirtz, Moritz
    Ryser, Alain
    Vogt, Julia E.
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [2] Supervising the Decoder of Variational Autoencoders to Improve Scientific Utility
    Tu, Liyun
    Talbot, Austin
    Gallagher, Neil M. M.
    Carlson, David E. E.
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2022, 70 : 5954 - 5966
  • [3] Nonlinear system identification using modified variational autoencoders
    Paniagua, Jose L.
    Lopez, Jesus A.
    INTELLIGENT SYSTEMS WITH APPLICATIONS, 2024, 22
  • [4] Direct Evolutionary Optimization of Variational Autoencoders with Binary Latents
    Drefs, Jakob
    Guiraud, Enrico
    Panagiotou, Filippos
    Luecke, Joerg
    MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2022, PT III, 2023, 13715 : 357 - 372
  • [5] Stochastic embeddings of dynamical phenomena through variational autoencoders
    Garcia, Constantino A.
    Felix, Paulo
    Presedo, Jesus M.
    Otero, Abraham
    JOURNAL OF COMPUTATIONAL PHYSICS, 2022, 454
  • [6] Recent Advances in Variational Autoencoders With Representation Learning for Biomedical Informatics: A Survey
    Wei, Ruoqi
    Mahmood, Ausif
    IEEE ACCESS, 2021, 9 : 4939 - 4956
  • [7] Φ-DVAE: Physics-informed dynamical variational autoencoders for unstructured data assimilation
    Glyn-Davies, Alex
    Duffin, Connor
    Akyildiz, O. Deniz
    Girolami, Mark
    JOURNAL OF COMPUTATIONAL PHYSICS, 2024, 515
  • [8] Deep image hashing based on twin-bottleneck hashing with variational autoencoders
    Verwilst, Maxim
    Zizakic, Nina
    Gu, Lingchen
    Pizurica, Aleksandra
    IEEE MMSP 2021: 2021 IEEE 23RD INTERNATIONAL WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING (MMSP), 2021,
  • [9] PriorVAE: encoding spatial priors with variational autoencoders for small-area estimation
    Semenova, Elizaveta
    Xu, Yidan
    Howes, Adam
    Rashid, Theo
    Bhatt, Samir
    Mishra, Swapnil
    Flaxman, Seth
    JOURNAL OF THE ROYAL SOCIETY INTERFACE, 2022, 19 (191)
  • [10] Exploiting Linear Interpolation of Variational Autoencoders for Satisfying Preferences in Evolutionary Design Optimization
    Saha, Sneha
    Minku, Leandro L.
    Yao, Xin
    Senhoff, Bernhard
    Menzel, Stefan
    2021 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC 2021), 2021, : 1767 - 1776