Journal article · 2012 · Open access
Three Classes of Deep Learning Architectures and Their Applications: A Tutorial Survey
APSIPA Transactions on Signal and Information Processing · Published 1 January 2012
In brief
“Three Classes of Deep Learning Architectures and Their Applications: A Tutorial Survey” is a 2012 journal article by Li Deng, published in APSIPA Transactions on Signal and Information Processing. OpenAlex counts 111 citations as of 16 November 2026, which puts it in the top 7% of works published in 2012 by citations. It is open access under a CC BY-NC licence: the full text is free to read at APSIPA Transactions on Signal and Information Processing.
- Citations
- 111
- Most cited in
- 2017 (21)
- Field-weighted impact
- 2.81
- References
- 180
- Authors
- 1
Abstract
In this invited paper, my overview material on the same topic as presented in the plenary overview session of APSIPA-2011 and the tutorial material presented in the same conference (Deng, 2011) are expanded and updated to include more recent developments in deep learning. The previous and the updated materials cover both theory and applications, and analyze its future directions. The goal of this tutorial survey is to introduce the emerging area of deep learning or hierarchical learning to the APSIPA community. Deep learning refers to a class of machine learning techniques, developed largely since 2006, where many stages of nonlinear information processing in hierarchical architectures are exploited for pattern classification and for feature learning. In the more recent literature, it is also connected to representation learning, which involves a hierarchy of features or concepts where higher-level concepts are defined from lower-level ones and where the same lower-level concepts help to define higher-level ones. In this tutorial, a brief history of deep learning research is discussed first. Then, a classificatory scheme is developed to analyze and summarize major work reported in the deep learning literature. Using this scheme, I provide a taxonomy-oriented survey on the existing deep architectures and algorithms in the literature, and categorize them into three classes: generative, discriminative, and hybrid. Three representative deep architectures --deep auto-encoder, deep stacking network, and deep neural network (pre-trained with deep belief network) --one in each of the three classes, are presented in more detail. Next, selected applications of deep learning are reviewed in broad areas of signal and information processing including audio/speech, image/vision, multimodality, language modeling, natural language processing, and information retrieval. Finally, future directions of deep learning are discussed and analyzed.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Deng, L. (2012). Three Classes of Deep Learning Architectures and Their Applications: A Tutorial Survey. APSIPA Transactions on Signal and Information Processing. https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/Transactions-APSIPA.pdf
MLA 9
Deng, Li. “Three Classes of Deep Learning Architectures and Their Applications: A Tutorial Survey.” APSIPA Transactions on Signal and Information Processing, 2012. https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/Transactions-APSIPA.pdf.
Chicago
Deng, Li. 2012. “Three Classes of Deep Learning Architectures and Their Applications: A Tutorial Survey.” APSIPA Transactions on Signal and Information Processing. https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/Transactions-APSIPA.pdf.
Harvard
Deng, L. (2012) ‘Three Classes of Deep Learning Architectures and Their Applications: A Tutorial Survey’, APSIPA Transactions on Signal and Information Processing. Available at: https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/Transactions-APSIPA.pdf.
IEEE
L. Deng, “Three Classes of Deep Learning Architectures and Their Applications: A Tutorial Survey,” APSIPA Transactions on Signal and Information Processing, 2012.
BibTeX
@article{deng2012three,
title = {{Three Classes of Deep Learning Architectures and Their Applications: A Tutorial Survey}},
author = {Deng, Li},
journal = {APSIPA Transactions on Signal and Information Processing},
year = {2012},
url = {https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/Transactions-APSIPA.pdf}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2016 | 8 | |
| 2017 | 21 | |
| 2018 | 9 | |
| 2019 | 18 | |
| 2020 | 11 | |
| 2021 | 15 | |
| 2022 | 2 | |
| 2023 | 7 | |
| 2024 | 4 | |
| 2025 | 5 |
Its field-weighted citation impact is 2.81: it has been cited 2.81 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 learning
- hierarchical learning
- deep learning architectures
- generative models
- discriminative models
- hybrid model
- deep autoencoder
- deep belief network
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?
Deng, L. (2012). Three Classes of Deep Learning Architectures and Their Applications: A Tutorial Survey. APSIPA Transactions on Signal and Information Processing. https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/Transactions-APSIPA.pdf
How many times has this paper been cited?
111 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 APSIPA Transactions on Signal and Information Processing.
Who wrote this paper?
Li Deng.
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.