Journal article 685 views 101 downloads
Literature Review of Deep Network Compression
Informatics, Volume: 8, Issue: 4, Start page: 77
Swansea University Authors:
Xianghua Xie , Mark Jones
-
PDF | Version of Record
Copyright: © 2021 by the authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC-BY) Licence.
Download (232.3KB)
DOI (Published version): 10.3390/informatics8040077
Abstract
Deep networks often possess a vast number of parameters, and their significant redundancy in parameterization has become a widely-recognized property. This presents significant challenges and restricts many deep learning applications, making the focus on reducing the complexity of models while maint...
Published in: | Informatics |
---|---|
ISSN: | 2227-9709 |
Published: |
MDPI AG
2021
|
Online Access: |
Check full text
|
URI: | https://cronfa.swan.ac.uk/Record/cronfa58687 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
first_indexed |
2021-11-17T08:30:38Z |
---|---|
last_indexed |
2021-12-08T04:18:54Z |
id |
cronfa58687 |
recordtype |
SURis |
fullrecord |
<?xml version="1.0"?><rfc1807><datestamp>2021-12-07T15:00:58.5976893</datestamp><bib-version>v2</bib-version><id>58687</id><entry>2021-11-17</entry><title>Literature Review of Deep Network Compression</title><swanseaauthors><author><sid>b334d40963c7a2f435f06d2c26c74e11</sid><ORCID>0000-0002-2701-8660</ORCID><firstname>Xianghua</firstname><surname>Xie</surname><name>Xianghua Xie</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>2e1030b6e14fc9debd5d5ae7cc335562</sid><ORCID>0000-0001-8991-1190</ORCID><firstname>Mark</firstname><surname>Jones</surname><name>Mark Jones</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-11-17</date><deptcode>SCS</deptcode><abstract>Deep networks often possess a vast number of parameters, and their significant redundancy in parameterization has become a widely-recognized property. This presents significant challenges and restricts many deep learning applications, making the focus on reducing the complexity of models while maintaining their powerful performance. In this paper, we present an overview of popular methods and review recent works on compressing and accelerating deep neural networks. We consider not only pruning methods but also quantization methods, and low-rank factorization methods. This review also intends to clarify these major concepts, and highlights their characteristics, advantages, and shortcomings.</abstract><type>Journal Article</type><journal>Informatics</journal><volume>8</volume><journalNumber>4</journalNumber><paginationStart>77</paginationStart><paginationEnd/><publisher>MDPI AG</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>2227-9709</issnElectronic><keywords>deep learning; neural networks pruning; model compression</keywords><publishedDay>17</publishedDay><publishedMonth>11</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-11-17</publishedDate><doi>10.3390/informatics8040077</doi><url/><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm>Another institution paid the OA fee</apcterm><funders>This work was supported by the Deanship of Scientific Research, King Khalid University
of Kingdom of Saudi Arabia under research grant number (RGP1/207/42).</funders><lastEdited>2021-12-07T15:00:58.5976893</lastEdited><Created>2021-11-17T08:26:18.4110099</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Ali</firstname><surname>Alqahtani</surname><order>1</order></author><author><firstname>Xianghua</firstname><surname>Xie</surname><orcid>0000-0002-2701-8660</orcid><order>2</order></author><author><firstname>Mark</firstname><surname>Jones</surname><orcid>0000-0001-8991-1190</orcid><order>3</order></author></authors><documents><document><filename>58687__21577__b2f1ed63dee54d52899d3e28bf731e58.pdf</filename><originalFilename>58687.VOR.pdf</originalFilename><uploaded>2021-11-18T13:00:40.8878145</uploaded><type>Output</type><contentLength>237872</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>Copyright: © 2021 by the authors. This article is an open access article
distributed under the terms and conditions of the Creative Commons Attribution (CC-BY) Licence.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807> |
spelling |
2021-12-07T15:00:58.5976893 v2 58687 2021-11-17 Literature Review of Deep Network Compression b334d40963c7a2f435f06d2c26c74e11 0000-0002-2701-8660 Xianghua Xie Xianghua Xie true false 2e1030b6e14fc9debd5d5ae7cc335562 0000-0001-8991-1190 Mark Jones Mark Jones true false 2021-11-17 SCS Deep networks often possess a vast number of parameters, and their significant redundancy in parameterization has become a widely-recognized property. This presents significant challenges and restricts many deep learning applications, making the focus on reducing the complexity of models while maintaining their powerful performance. In this paper, we present an overview of popular methods and review recent works on compressing and accelerating deep neural networks. We consider not only pruning methods but also quantization methods, and low-rank factorization methods. This review also intends to clarify these major concepts, and highlights their characteristics, advantages, and shortcomings. Journal Article Informatics 8 4 77 MDPI AG 2227-9709 deep learning; neural networks pruning; model compression 17 11 2021 2021-11-17 10.3390/informatics8040077 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University Another institution paid the OA fee This work was supported by the Deanship of Scientific Research, King Khalid University of Kingdom of Saudi Arabia under research grant number (RGP1/207/42). 2021-12-07T15:00:58.5976893 2021-11-17T08:26:18.4110099 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Ali Alqahtani 1 Xianghua Xie 0000-0002-2701-8660 2 Mark Jones 0000-0001-8991-1190 3 58687__21577__b2f1ed63dee54d52899d3e28bf731e58.pdf 58687.VOR.pdf 2021-11-18T13:00:40.8878145 Output 237872 application/pdf Version of Record true Copyright: © 2021 by the authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC-BY) Licence. true eng https://creativecommons.org/licenses/by/4.0/ |
title |
Literature Review of Deep Network Compression |
spellingShingle |
Literature Review of Deep Network Compression Xianghua Xie Mark Jones |
title_short |
Literature Review of Deep Network Compression |
title_full |
Literature Review of Deep Network Compression |
title_fullStr |
Literature Review of Deep Network Compression |
title_full_unstemmed |
Literature Review of Deep Network Compression |
title_sort |
Literature Review of Deep Network Compression |
author_id_str_mv |
b334d40963c7a2f435f06d2c26c74e11 2e1030b6e14fc9debd5d5ae7cc335562 |
author_id_fullname_str_mv |
b334d40963c7a2f435f06d2c26c74e11_***_Xianghua Xie 2e1030b6e14fc9debd5d5ae7cc335562_***_Mark Jones |
author |
Xianghua Xie Mark Jones |
author2 |
Ali Alqahtani Xianghua Xie Mark Jones |
format |
Journal article |
container_title |
Informatics |
container_volume |
8 |
container_issue |
4 |
container_start_page |
77 |
publishDate |
2021 |
institution |
Swansea University |
issn |
2227-9709 |
doi_str_mv |
10.3390/informatics8040077 |
publisher |
MDPI AG |
college_str |
Faculty of Science and Engineering |
hierarchytype |
|
hierarchy_top_id |
facultyofscienceandengineering |
hierarchy_top_title |
Faculty of Science and Engineering |
hierarchy_parent_id |
facultyofscienceandengineering |
hierarchy_parent_title |
Faculty of Science and Engineering |
department_str |
School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science |
document_store_str |
1 |
active_str |
0 |
description |
Deep networks often possess a vast number of parameters, and their significant redundancy in parameterization has become a widely-recognized property. This presents significant challenges and restricts many deep learning applications, making the focus on reducing the complexity of models while maintaining their powerful performance. In this paper, we present an overview of popular methods and review recent works on compressing and accelerating deep neural networks. We consider not only pruning methods but also quantization methods, and low-rank factorization methods. This review also intends to clarify these major concepts, and highlights their characteristics, advantages, and shortcomings. |
published_date |
2021-11-17T04:15:24Z |
_version_ |
1763754036127858688 |
score |
11.016235 |