Back
Fulltext
Journal article

Probabilistic models with deep neural networks

  • Masegosa, Andrés R. Department of Mathematics, Center for the Development and Transfer of Mathematical Research to Industry (CDTIME), University of Almería, Spain
  • Cabañas, Rafael Istituto Dalle Molle di studi sull'intelligenza artificiale (IDSIA), Facoltà di scienze informatiche, Università della Svizzera italiana, Svizzera
  • Langseth, Helge Department of Computer Science, Norwegian University of Science and Technology, Trondheim, Norway
  • Nielsen, Thomas D. Department of Computer Science, Aalborg University, Denmark
  • Salmerón, Antonio Department of Mathematics, Center for the Development and Transfer of Mathematical Research to Industry (CDTIME), University of Almería, Spain
Show more…
    18.01.2021
Published in:
  • Entropy. - 2021, vol. 23, no. 1, p. 27 p
Deep probabilistic modeling
Variational inference
Neural networks
Latent variable models
Bayesian learning
English Recent advances in statistical inference have significantly expanded the toolbox of probabilistic modeling. Historically, probabilistic modeling has been constrained to very restricted model classes, where exact or approximate probabilistic inference is feasible. However, developments in variational inference, a general form of approximate probabilistic inference that originated in statistical physics, have enabled probabilistic modeling to overcome these limitations: (i) Approximate probabilistic inference is now possible over a broad class of probabilistic models containing a large number of parameters, and (ii) scalable inference methods based on stochastic gradient descent and distributed computing engines allow probabilistic modeling to be applied to massive data sets. One important practical consequence of these advances is the possibility to include deep neural networks within probabilistic models, thereby capturing complex non- linear stochastic relationships between the random variables. These advances, in conjunction with the release of novel probabilistic modeling toolboxes, have greatly expanded the scope of applications of probabilistic models, and allowed the models to take advantage of the recent strides made by the deep learning community. In this paper, we provide an overview of the main concepts, methods, and tools needed to use deep neural networks within a probabilistic modeling framework.
Language
  • English
Classification
Computer science and technology
License
License undefined
Identifiers
Persistent URL
https://n2t.net/ark:/12658/srd1319186
Statistics
Document views: 40 File downloads:
  • Cabanas_2021_MDPI_entropy.pdf: 69