Structured Convolution Matrices for Energy-efficient Deep learning
We derive a relationship between network representation in energy-efficient neuromorphic architectures and block Toplitz convolutional matrices. Inspired by this connection, we develop deep convolutional networks using a family of structured convolutional matrices and achieve state-of-the-art trade-...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Appuswamy, Rathinakumar Nayak, Tapan Arthur, John Esser, Steven Merolla, Paul Mckinstry, Jeffrey Melano, Timothy Flickner, Myron Modha, Dharmendra |
| description | We derive a relationship between network representation in energy-efficient
neuromorphic architectures and block Toplitz convolutional matrices. Inspired
by this connection, we develop deep convolutional networks using a family of
structured convolutional matrices and achieve state-of-the-art trade-off
between energy efficiency and classification accuracy for well-known image
recognition tasks. We also put forward a novel method to train binary
convolutional networks by utilising an existing connection between
noisy-rectified linear units and binary activations. |
| doi_str_mv | 10.48550/arxiv.1606.02407 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1606_02407</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1606_02407</sourcerecordid><originalsourceid>FETCH-LOGICAL-a1157-7e0228c7b918cad59a9b48bd475079924b2bcac589782d6afa29f76dc3bbd5033</originalsourceid><addsrcrecordid>eNotz81OAyEUQGE2Lkz1AVzJC8wIDAyw1LH-JG1cqOvJBS4Nycg0lGns2xurq7M7yUfIDWetNEqxOyjf6djynvUtE5LpS_LwXsvi61Iw0GHOx3laapoz3UItyeOBxrnQdcayOzUYY_IJc6WPiHs6IZSc8u6KXESYDnj93xX5fFp_DC_N5u35dbjfNMC50o1GJoTx2lluPARlwTppXJBaMW2tkE44D14Zq40IPUQQNuo--M65oFjXrcjt3_esGPclfUE5jb-a8azpfgBPo0VW</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Structured Convolution Matrices for Energy-efficient Deep learning</title><source>arXiv.org</source><creator>Appuswamy, Rathinakumar ; Nayak, Tapan ; Arthur, John ; Esser, Steven ; Merolla, Paul ; Mckinstry, Jeffrey ; Melano, Timothy ; Flickner, Myron ; Modha, Dharmendra</creator><creatorcontrib>Appuswamy, Rathinakumar ; Nayak, Tapan ; Arthur, John ; Esser, Steven ; Merolla, Paul ; Mckinstry, Jeffrey ; Melano, Timothy ; Flickner, Myron ; Modha, Dharmendra</creatorcontrib><description>We derive a relationship between network representation in energy-efficient
neuromorphic architectures and block Toplitz convolutional matrices. Inspired
by this connection, we develop deep convolutional networks using a family of
structured convolutional matrices and achieve state-of-the-art trade-off
between energy efficiency and classification accuracy for well-known image
recognition tasks. We also put forward a novel method to train binary
convolutional networks by utilising an existing connection between
noisy-rectified linear units and binary activations.</description><identifier>DOI: 10.48550/arxiv.1606.02407</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Learning ; Computer Science - Neural and Evolutionary Computing</subject><creationdate>2016-06</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-a1157-7e0228c7b918cad59a9b48bd475079924b2bcac589782d6afa29f76dc3bbd5033</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1606.02407$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1606.02407$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Appuswamy, Rathinakumar</creatorcontrib><creatorcontrib>Nayak, Tapan</creatorcontrib><creatorcontrib>Arthur, John</creatorcontrib><creatorcontrib>Esser, Steven</creatorcontrib><creatorcontrib>Merolla, Paul</creatorcontrib><creatorcontrib>Mckinstry, Jeffrey</creatorcontrib><creatorcontrib>Melano, Timothy</creatorcontrib><creatorcontrib>Flickner, Myron</creatorcontrib><creatorcontrib>Modha, Dharmendra</creatorcontrib><title>Structured Convolution Matrices for Energy-efficient Deep learning</title><description>We derive a relationship between network representation in energy-efficient
neuromorphic architectures and block Toplitz convolutional matrices. Inspired
by this connection, we develop deep convolutional networks using a family of
structured convolutional matrices and achieve state-of-the-art trade-off
between energy efficiency and classification accuracy for well-known image
recognition tasks. We also put forward a novel method to train binary
convolutional networks by utilising an existing connection between
noisy-rectified linear units and binary activations.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Learning</subject><subject>Computer Science - Neural and Evolutionary Computing</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2016</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz81OAyEUQGE2Lkz1AVzJC8wIDAyw1LH-JG1cqOvJBS4Nycg0lGns2xurq7M7yUfIDWetNEqxOyjf6djynvUtE5LpS_LwXsvi61Iw0GHOx3laapoz3UItyeOBxrnQdcayOzUYY_IJc6WPiHs6IZSc8u6KXESYDnj93xX5fFp_DC_N5u35dbjfNMC50o1GJoTx2lluPARlwTppXJBaMW2tkE44D14Zq40IPUQQNuo--M65oFjXrcjt3_esGPclfUE5jb-a8azpfgBPo0VW</recordid><startdate>20160608</startdate><enddate>20160608</enddate><creator>Appuswamy, Rathinakumar</creator><creator>Nayak, Tapan</creator><creator>Arthur, John</creator><creator>Esser, Steven</creator><creator>Merolla, Paul</creator><creator>Mckinstry, Jeffrey</creator><creator>Melano, Timothy</creator><creator>Flickner, Myron</creator><creator>Modha, Dharmendra</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20160608</creationdate><title>Structured Convolution Matrices for Energy-efficient Deep learning</title><author>Appuswamy, Rathinakumar ; Nayak, Tapan ; Arthur, John ; Esser, Steven ; Merolla, Paul ; Mckinstry, Jeffrey ; Melano, Timothy ; Flickner, Myron ; Modha, Dharmendra</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a1157-7e0228c7b918cad59a9b48bd475079924b2bcac589782d6afa29f76dc3bbd5033</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2016</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Learning</topic><topic>Computer Science - Neural and Evolutionary Computing</topic><toplevel>online_resources</toplevel><creatorcontrib>Appuswamy, Rathinakumar</creatorcontrib><creatorcontrib>Nayak, Tapan</creatorcontrib><creatorcontrib>Arthur, John</creatorcontrib><creatorcontrib>Esser, Steven</creatorcontrib><creatorcontrib>Merolla, Paul</creatorcontrib><creatorcontrib>Mckinstry, Jeffrey</creatorcontrib><creatorcontrib>Melano, Timothy</creatorcontrib><creatorcontrib>Flickner, Myron</creatorcontrib><creatorcontrib>Modha, Dharmendra</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Appuswamy, Rathinakumar</au><au>Nayak, Tapan</au><au>Arthur, John</au><au>Esser, Steven</au><au>Merolla, Paul</au><au>Mckinstry, Jeffrey</au><au>Melano, Timothy</au><au>Flickner, Myron</au><au>Modha, Dharmendra</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Structured Convolution Matrices for Energy-efficient Deep learning</atitle><date>2016-06-08</date><risdate>2016</risdate><abstract>We derive a relationship between network representation in energy-efficient
neuromorphic architectures and block Toplitz convolutional matrices. Inspired
by this connection, we develop deep convolutional networks using a family of
structured convolutional matrices and achieve state-of-the-art trade-off
between energy efficiency and classification accuracy for well-known image
recognition tasks. We also put forward a novel method to train binary
convolutional networks by utilising an existing connection between
noisy-rectified linear units and binary activations.</abstract><doi>10.48550/arxiv.1606.02407</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.1606.02407 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_1606_02407 |
| source | arXiv.org |
| subjects | Computer Science - Artificial Intelligence Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning Computer Science - Neural and Evolutionary Computing |
| title | Structured Convolution Matrices for Energy-efficient Deep learning |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T02%3A01%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Structured%20Convolution%20Matrices%20for%20Energy-efficient%20Deep%20learning&rft.au=Appuswamy,%20Rathinakumar&rft.date=2016-06-08&rft_id=info:doi/10.48550/arxiv.1606.02407&rft_dat=%3Carxiv_GOX%3E1606_02407%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |