Review article · 2015 · Open access
Learning Deep Generative Models
Annual Review of Statistics and Its Application, 2(1), 361–385 · Published 10 April 2015 · DOI 10.1146/annurev-statistics-010814-020120
In brief
“Learning Deep Generative Models” is a 2015 review article by Ruslan Salakhutdinov, published in Annual Review of Statistics and Its Application. OpenAlex counts 451 citations as of 16 November 2026, which puts it in the top 2% of works published in 2015 by citations. It is open access: the full text is free to read at Annual Review of Statistics and Its Application.
- Citations
- 451
- Most cited in
- 2021 (53)
- Field-weighted impact
- 1.23
- References
- 98
- Authors
- 1
Abstract
Building intelligent systems that are capable of extracting high-level representations from high-dimensional sensory data lies at the core of solving many artificial intelligence–related tasks, including object recognition, speech perception, and language understanding. Theoretical and biological arguments strongly suggest that building such systems requires models with deep architectures that involve many layers of nonlinear processing. In this article, we review several popular deep learning models, including deep belief networks and deep Boltzmann machines. We show that (a) these deep generative models, which contain many layers of latent variables and millions of parameters, can be learned efficiently, and (b) the learned high-level feature representations can be successfully applied in many application domains, including visual object recognition, information retrieval, classification, and regression tasks.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Salakhutdinov, R. (2015). Learning Deep Generative Models. Annual Review of Statistics and Its Application, 2(1), 361–385. https://doi.org/10.1146/annurev-statistics-010814-020120
MLA 9
Salakhutdinov, Ruslan. “Learning Deep Generative Models.” Annual Review of Statistics and Its Application, vol. 2, no. 1, 2015, pp. 361–385. https://doi.org/10.1146/annurev-statistics-010814-020120.
Chicago
Salakhutdinov, Ruslan. 2015. “Learning Deep Generative Models.” Annual Review of Statistics and Its Application 2 (1): 361–385. https://doi.org/10.1146/annurev-statistics-010814-020120.
Harvard
Salakhutdinov, R. (2015) ‘Learning Deep Generative Models’, Annual Review of Statistics and Its Application, 2(1), pp. 361–385. doi:10.1146/annurev-statistics-010814-020120.
IEEE
R. Salakhutdinov, “Learning Deep Generative Models,” Annual Review of Statistics and Its Application, vol. 2, no. 1, pp. 361–385, 2015, doi: 10.1146/annurev-statistics-010814-020120.
BibTeX
@article{salakhutdinov2015learning,
title = {{Learning Deep Generative Models}},
author = {Salakhutdinov, Ruslan},
journal = {Annual Review of Statistics and Its Application},
year = {2015},
volume = {2},
number = {1},
pages = {361--385},
doi = {10.1146/annurev-statistics-010814-020120},
url = {https://doi.org/10.1146/annurev-statistics-010814-020120}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2017 | 34 | |
| 2018 | 39 | |
| 2019 | 42 | |
| 2020 | 37 | |
| 2021 | 53 | |
| 2022 | 28 | |
| 2023 | 32 | |
| 2024 | 45 | |
| 2025 | 39 | |
| 2026 | 17 |
Its field-weighted citation impact is 1.23: it has been cited 1.23 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- deep generative models
- deep belief network
- deep Boltzmann machine
- latent variable models
- unsupervised learning
- deep learning
- object recognition
- information retrieval
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Salakhutdinov, R. (2015). Learning Deep Generative Models. Annual Review of Statistics and Its Application, 2(1), 361–385. https://doi.org/10.1146/annurev-statistics-010814-020120
How many times has this paper been cited?
451 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access: read the free full text at Annual Review of Statistics and Its Application.
Who wrote this paper?
Ruslan Salakhutdinov.
What is the DOI of this paper?
10.1146/annurev-statistics-010814-020120. The permanent link is https://doi.org/10.1146/annurev-statistics-010814-020120.
Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.