A survey on deep learning

Algorithms, techniques, and applications

Samira Pouyanfar, Saad Sadiq, Yilin Yan, Haiman Tian, Yudong Tao, Maria Presa Reyes, Mei-Ling Shyu, Shu Ching Chen, S. S. Iyengar

Research output: Contribution to journalReview article

20 Citations (Scopus)

Abstract

The field of machine learning is witnessing its golden era as deep learning slowly becomes the leader in this domain. Deep learning uses multiple layers to represent the abstractions of data to build computational models. Some key enabler deep learning algorithms such as generative adversarial networks, convolutional neural networks, and model transfers have completely changed our perception of information processing. However, there exists an aperture of understanding behind this tremendously fast-paced domain, because it was never previously represented from a multiscope perspective. The lack of core understanding renders these powerful methods as black-box machines that inhibit development at a fundamental level. Moreover, deep learning has repeatedly been perceived as a silver bullet to all stumbling blocks in machine learning, which is far from the truth. This article presents a comprehensive review of historical and recent state-of-theart approaches in visual, audio, and text processing; social network analysis; and natural language processing, followed by the in-depth analysis on pivoting and groundbreaking advances in deep learning applications. It was also undertaken to review the issues faced in deep learning such as unsupervised learning, black-box models, and online learning and to illustrate how these challenges can be transformed into prolific future research avenues.

Original languageEnglish (US)
Article number92
JournalACM Computing Surveys
Volume51
Issue number5
DOIs
StatePublished - Aug 1 2018

Fingerprint

Learning algorithms
Learning Algorithm
Black Box
Machine Learning
Learning systems
Text Processing
Social Network Analysis
Pivoting
Online Learning
Text processing
Unsupervised Learning
Silver
Unsupervised learning
Information Processing
Computational Model
Natural Language
Electric network analysis
Learning
Deep learning
Neural Networks

Keywords

  • Big data
  • Deep learning
  • Distributed processing
  • Machine learning
  • Neural networks
  • Survey

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Cite this

Pouyanfar, S., Sadiq, S., Yan, Y., Tian, H., Tao, Y., Reyes, M. P., ... Iyengar, S. S. (2018). A survey on deep learning: Algorithms, techniques, and applications. ACM Computing Surveys, 51(5), [92]. https://doi.org/10.1145/3234150

A survey on deep learning : Algorithms, techniques, and applications. / Pouyanfar, Samira; Sadiq, Saad; Yan, Yilin; Tian, Haiman; Tao, Yudong; Reyes, Maria Presa; Shyu, Mei-Ling; Chen, Shu Ching; Iyengar, S. S.

In: ACM Computing Surveys, Vol. 51, No. 5, 92, 01.08.2018.

Research output: Contribution to journalReview article

Pouyanfar, S, Sadiq, S, Yan, Y, Tian, H, Tao, Y, Reyes, MP, Shyu, M-L, Chen, SC & Iyengar, SS 2018, 'A survey on deep learning: Algorithms, techniques, and applications', ACM Computing Surveys, vol. 51, no. 5, 92. https://doi.org/10.1145/3234150
Pouyanfar S, Sadiq S, Yan Y, Tian H, Tao Y, Reyes MP et al. A survey on deep learning: Algorithms, techniques, and applications. ACM Computing Surveys. 2018 Aug 1;51(5). 92. https://doi.org/10.1145/3234150
Pouyanfar, Samira ; Sadiq, Saad ; Yan, Yilin ; Tian, Haiman ; Tao, Yudong ; Reyes, Maria Presa ; Shyu, Mei-Ling ; Chen, Shu Ching ; Iyengar, S. S. / A survey on deep learning : Algorithms, techniques, and applications. In: ACM Computing Surveys. 2018 ; Vol. 51, No. 5.
@article{a7011bebf39f4a11ad025afceaffa443,
title = "A survey on deep learning: Algorithms, techniques, and applications",
abstract = "The field of machine learning is witnessing its golden era as deep learning slowly becomes the leader in this domain. Deep learning uses multiple layers to represent the abstractions of data to build computational models. Some key enabler deep learning algorithms such as generative adversarial networks, convolutional neural networks, and model transfers have completely changed our perception of information processing. However, there exists an aperture of understanding behind this tremendously fast-paced domain, because it was never previously represented from a multiscope perspective. The lack of core understanding renders these powerful methods as black-box machines that inhibit development at a fundamental level. Moreover, deep learning has repeatedly been perceived as a silver bullet to all stumbling blocks in machine learning, which is far from the truth. This article presents a comprehensive review of historical and recent state-of-theart approaches in visual, audio, and text processing; social network analysis; and natural language processing, followed by the in-depth analysis on pivoting and groundbreaking advances in deep learning applications. It was also undertaken to review the issues faced in deep learning such as unsupervised learning, black-box models, and online learning and to illustrate how these challenges can be transformed into prolific future research avenues.",
keywords = "Big data, Deep learning, Distributed processing, Machine learning, Neural networks, Survey",
author = "Samira Pouyanfar and Saad Sadiq and Yilin Yan and Haiman Tian and Yudong Tao and Reyes, {Maria Presa} and Mei-Ling Shyu and Chen, {Shu Ching} and Iyengar, {S. S.}",
year = "2018",
month = "8",
day = "1",
doi = "10.1145/3234150",
language = "English (US)",
volume = "51",
journal = "ACM Computing Surveys",
issn = "0360-0300",
publisher = "Association for Computing Machinery (ACM)",
number = "5",

}

TY - JOUR

T1 - A survey on deep learning

T2 - Algorithms, techniques, and applications

AU - Pouyanfar, Samira

AU - Sadiq, Saad

AU - Yan, Yilin

AU - Tian, Haiman

AU - Tao, Yudong

AU - Reyes, Maria Presa

AU - Shyu, Mei-Ling

AU - Chen, Shu Ching

AU - Iyengar, S. S.

PY - 2018/8/1

Y1 - 2018/8/1

N2 - The field of machine learning is witnessing its golden era as deep learning slowly becomes the leader in this domain. Deep learning uses multiple layers to represent the abstractions of data to build computational models. Some key enabler deep learning algorithms such as generative adversarial networks, convolutional neural networks, and model transfers have completely changed our perception of information processing. However, there exists an aperture of understanding behind this tremendously fast-paced domain, because it was never previously represented from a multiscope perspective. The lack of core understanding renders these powerful methods as black-box machines that inhibit development at a fundamental level. Moreover, deep learning has repeatedly been perceived as a silver bullet to all stumbling blocks in machine learning, which is far from the truth. This article presents a comprehensive review of historical and recent state-of-theart approaches in visual, audio, and text processing; social network analysis; and natural language processing, followed by the in-depth analysis on pivoting and groundbreaking advances in deep learning applications. It was also undertaken to review the issues faced in deep learning such as unsupervised learning, black-box models, and online learning and to illustrate how these challenges can be transformed into prolific future research avenues.

AB - The field of machine learning is witnessing its golden era as deep learning slowly becomes the leader in this domain. Deep learning uses multiple layers to represent the abstractions of data to build computational models. Some key enabler deep learning algorithms such as generative adversarial networks, convolutional neural networks, and model transfers have completely changed our perception of information processing. However, there exists an aperture of understanding behind this tremendously fast-paced domain, because it was never previously represented from a multiscope perspective. The lack of core understanding renders these powerful methods as black-box machines that inhibit development at a fundamental level. Moreover, deep learning has repeatedly been perceived as a silver bullet to all stumbling blocks in machine learning, which is far from the truth. This article presents a comprehensive review of historical and recent state-of-theart approaches in visual, audio, and text processing; social network analysis; and natural language processing, followed by the in-depth analysis on pivoting and groundbreaking advances in deep learning applications. It was also undertaken to review the issues faced in deep learning such as unsupervised learning, black-box models, and online learning and to illustrate how these challenges can be transformed into prolific future research avenues.

KW - Big data

KW - Deep learning

KW - Distributed processing

KW - Machine learning

KW - Neural networks

KW - Survey

UR - http://www.scopus.com/inward/record.url?scp=85053880872&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053880872&partnerID=8YFLogxK

U2 - 10.1145/3234150

DO - 10.1145/3234150

M3 - Review article

VL - 51

JO - ACM Computing Surveys

JF - ACM Computing Surveys

SN - 0360-0300

IS - 5

M1 - 92

ER -