Intra-layer Nonuniform Quantization for Deep Convolutional Neural Network
Deep convolutional neural network (DCNN) has achieved remarkable performance on object detection and speech recognition in recent years. However, the excellent performance of a DCNN incurs high computational complexity and large memory requirement. In this paper, an equal distance nonuniform quantiz...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2016-08 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Sun, Fangxuan Lin, Jun Wang, Zhongfeng |
| description | Deep convolutional neural network (DCNN) has achieved remarkable performance on object detection and speech recognition in recent years. However, the excellent performance of a DCNN incurs high computational complexity and large memory requirement. In this paper, an equal distance nonuniform quantization (ENQ) scheme and a K-means clustering nonuniform quantization (KNQ) scheme are proposed to reduce the required memory storage when low complexity hardware or software implementations are considered. For the VGG-16 and the AlexNet, the proposed nonuniform quantization schemes reduce the number of required memory storage by approximately 50\% while achieving almost the same or even better classification accuracy compared to the state-of-the-art quantization method. Compared to the ENQ scheme, the proposed KNQ scheme provides a better tradeoff when higher accuracy is required. |
| format | Article |
| fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2080241518</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2080241518</sourcerecordid><originalsourceid>FETCH-proquest_journals_20802415183</originalsourceid><addsrcrecordid>eNqNi0EKwjAQAIMgWLR_CHgupJtGe6-KvRQE7yWHFFpjtm4SRV9vFR_gaWCYmbEEpMyzsgBYsNT7QQgBmy0oJRNW1y6Qzqx-GuINuuj6DunKT1G70L906NHxyfCdMSOv0N3Rxo_Uljcm0hfhgXRZsXmnrTfpj0u2PuzP1TEbCW_R-NAOGGn6fAuiFFDkKi_lf9Ub0MQ86Q</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2080241518</pqid></control><display><type>article</type><title>Intra-layer Nonuniform Quantization for Deep Convolutional Neural Network</title><source>Free E- Journals</source><creator>Sun, Fangxuan ; Lin, Jun ; Wang, Zhongfeng</creator><creatorcontrib>Sun, Fangxuan ; Lin, Jun ; Wang, Zhongfeng</creatorcontrib><description>Deep convolutional neural network (DCNN) has achieved remarkable performance on object detection and speech recognition in recent years. However, the excellent performance of a DCNN incurs high computational complexity and large memory requirement. In this paper, an equal distance nonuniform quantization (ENQ) scheme and a K-means clustering nonuniform quantization (KNQ) scheme are proposed to reduce the required memory storage when low complexity hardware or software implementations are considered. For the VGG-16 and the AlexNet, the proposed nonuniform quantization schemes reduce the number of required memory storage by approximately 50\% while achieving almost the same or even better classification accuracy compared to the state-of-the-art quantization method. Compared to the ENQ scheme, the proposed KNQ scheme provides a better tradeoff when higher accuracy is required.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial neural networks ; Cluster analysis ; Clustering ; Complexity ; Computer memory ; Measurement ; Neural networks ; Object recognition ; Speech recognition ; Vector quantization</subject><ispartof>arXiv.org, 2016-08</ispartof><rights>2016. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Sun, Fangxuan</creatorcontrib><creatorcontrib>Lin, Jun</creatorcontrib><creatorcontrib>Wang, Zhongfeng</creatorcontrib><title>Intra-layer Nonuniform Quantization for Deep Convolutional Neural Network</title><title>arXiv.org</title><description>Deep convolutional neural network (DCNN) has achieved remarkable performance on object detection and speech recognition in recent years. However, the excellent performance of a DCNN incurs high computational complexity and large memory requirement. In this paper, an equal distance nonuniform quantization (ENQ) scheme and a K-means clustering nonuniform quantization (KNQ) scheme are proposed to reduce the required memory storage when low complexity hardware or software implementations are considered. For the VGG-16 and the AlexNet, the proposed nonuniform quantization schemes reduce the number of required memory storage by approximately 50\% while achieving almost the same or even better classification accuracy compared to the state-of-the-art quantization method. Compared to the ENQ scheme, the proposed KNQ scheme provides a better tradeoff when higher accuracy is required.</description><subject>Artificial neural networks</subject><subject>Cluster analysis</subject><subject>Clustering</subject><subject>Complexity</subject><subject>Computer memory</subject><subject>Measurement</subject><subject>Neural networks</subject><subject>Object recognition</subject><subject>Speech recognition</subject><subject>Vector quantization</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2016</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNi0EKwjAQAIMgWLR_CHgupJtGe6-KvRQE7yWHFFpjtm4SRV9vFR_gaWCYmbEEpMyzsgBYsNT7QQgBmy0oJRNW1y6Qzqx-GuINuuj6DunKT1G70L906NHxyfCdMSOv0N3Rxo_Uljcm0hfhgXRZsXmnrTfpj0u2PuzP1TEbCW_R-NAOGGn6fAuiFFDkKi_lf9Ub0MQ86Q</recordid><startdate>20160806</startdate><enddate>20160806</enddate><creator>Sun, Fangxuan</creator><creator>Lin, Jun</creator><creator>Wang, Zhongfeng</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20160806</creationdate><title>Intra-layer Nonuniform Quantization for Deep Convolutional Neural Network</title><author>Sun, Fangxuan ; Lin, Jun ; Wang, Zhongfeng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_20802415183</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2016</creationdate><topic>Artificial neural networks</topic><topic>Cluster analysis</topic><topic>Clustering</topic><topic>Complexity</topic><topic>Computer memory</topic><topic>Measurement</topic><topic>Neural networks</topic><topic>Object recognition</topic><topic>Speech recognition</topic><topic>Vector quantization</topic><toplevel>online_resources</toplevel><creatorcontrib>Sun, Fangxuan</creatorcontrib><creatorcontrib>Lin, Jun</creatorcontrib><creatorcontrib>Wang, Zhongfeng</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Sun, Fangxuan</au><au>Lin, Jun</au><au>Wang, Zhongfeng</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Intra-layer Nonuniform Quantization for Deep Convolutional Neural Network</atitle><jtitle>arXiv.org</jtitle><date>2016-08-06</date><risdate>2016</risdate><eissn>2331-8422</eissn><abstract>Deep convolutional neural network (DCNN) has achieved remarkable performance on object detection and speech recognition in recent years. However, the excellent performance of a DCNN incurs high computational complexity and large memory requirement. In this paper, an equal distance nonuniform quantization (ENQ) scheme and a K-means clustering nonuniform quantization (KNQ) scheme are proposed to reduce the required memory storage when low complexity hardware or software implementations are considered. For the VGG-16 and the AlexNet, the proposed nonuniform quantization schemes reduce the number of required memory storage by approximately 50\% while achieving almost the same or even better classification accuracy compared to the state-of-the-art quantization method. Compared to the ENQ scheme, the proposed KNQ scheme provides a better tradeoff when higher accuracy is required.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2016-08 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_proquest_journals_2080241518 |
| source | Free E- Journals |
| subjects | Artificial neural networks Cluster analysis Clustering Complexity Computer memory Measurement Neural networks Object recognition Speech recognition Vector quantization |
| title | Intra-layer Nonuniform Quantization for Deep Convolutional Neural Network |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-10T22%3A07%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Intra-layer%20Nonuniform%20Quantization%20for%20Deep%20Convolutional%20Neural%20Network&rft.jtitle=arXiv.org&rft.au=Sun,%20Fangxuan&rft.date=2016-08-06&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2080241518%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2080241518&rft_id=info:pmid/&rfr_iscdi=true |