Intelligent Network-on-Chip With Online Reinforcement Learning for Portable HD Object Recognition Processor
An intelligent Reinforcement Learning (RL) Network-on-Chip (NoC) is proposed as a communication architecture of a heterogeneous many-core processor for portable HD object recognition. The proposed RL NoC automatically learns bandwidth adjustment and resource allocation in the heterogeneous many-core...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on circuits and systems. I, Regular papers Regular papers, 2014-02, Vol.61 (2), p.476-484 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 484 |
|---|---|
| container_issue | 2 |
| container_start_page | 476 |
| container_title | IEEE transactions on circuits and systems. I, Regular papers |
| container_volume | 61 |
| creator | Park, Junyoung Hong, Injoon Kim, Gyeonghoon Nam, Byeong-Gyu Yoo, Hoi-Jun |
| description | An intelligent Reinforcement Learning (RL) Network-on-Chip (NoC) is proposed as a communication architecture of a heterogeneous many-core processor for portable HD object recognition. The proposed RL NoC automatically learns bandwidth adjustment and resource allocation in the heterogeneous many-core processor without explicit modeling. By regulating the bandwidth and reallocating cores, the throughput performances of feature detection and description are increased by 20.4% and 11.5%, respectively. As a result, the overall execution time of the object recognition is reduced by 38%. The proposed processor with RL NoC is implemented in a 65 nm CMOS process, and it successfully demonstrates the real-time object recognition for a 720 p HD video stream while consuming 235 mW peak power at 200 MHz, 1.2 V. |
| doi_str_mv | 10.1109/TCSI.2013.2284188 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_TCSI_2013_2284188</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6642153</ieee_id><sourcerecordid>3238314441</sourcerecordid><originalsourceid>FETCH-LOGICAL-c326t-93e3406e70a3dda29c395a7a32b173e8127973de6f4e9ef5b1a32ff18f4c3ec43</originalsourceid><addsrcrecordid>eNpdkMFqGzEQQJfSQN20H1B6EeSSyzoaSbsrHYvTNgZTm8SlRyHLs7bsteRIMqF_n11scshphpk3w8wrim9AxwBU3S0nT9Mxo8DHjEkBUn4oRlBVsqSS1h-HXKhSciY_FZ9T2lHKFOUwKvZTn7Hr3AZ9Jn8wv4S4L4MvJ1t3JP9c3pK575xH8ojOtyFaPAzkDE30zm9IXyKLELNZdUge7sl8tUObe9qGjXfZBU8WMVhMKcQvxVVruoRfL_G6-Pvr53LyUM7mv6eTH7PSclbnUnHkgtbYUMPXa8OU5aoyjeFsBQ1HCaxRDV9j3QpU2FYr6FttC7IVlqMV_Lq4Pe89xvB8wpT1wSXbf2k8hlPSUMuqaYQSrEdv3qG7cIq-v05DRUUNEvhAwZmyMaQUsdXH6A4m_tdA9aBfD_r1oF9f9Pcz388zDhHf-LoWDCrOXwHz2IFM</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1504618132</pqid></control><display><type>article</type><title>Intelligent Network-on-Chip With Online Reinforcement Learning for Portable HD Object Recognition Processor</title><source>IEEE Electronic Library (IEL)</source><creator>Park, Junyoung ; Hong, Injoon ; Kim, Gyeonghoon ; Nam, Byeong-Gyu ; Yoo, Hoi-Jun</creator><creatorcontrib>Park, Junyoung ; Hong, Injoon ; Kim, Gyeonghoon ; Nam, Byeong-Gyu ; Yoo, Hoi-Jun</creatorcontrib><description>An intelligent Reinforcement Learning (RL) Network-on-Chip (NoC) is proposed as a communication architecture of a heterogeneous many-core processor for portable HD object recognition. The proposed RL NoC automatically learns bandwidth adjustment and resource allocation in the heterogeneous many-core processor without explicit modeling. By regulating the bandwidth and reallocating cores, the throughput performances of feature detection and description are increased by 20.4% and 11.5%, respectively. As a result, the overall execution time of the object recognition is reduced by 38%. The proposed processor with RL NoC is implemented in a 65 nm CMOS process, and it successfully demonstrates the real-time object recognition for a 720 p HD video stream while consuming 235 mW peak power at 200 MHz, 1.2 V.</description><identifier>ISSN: 1549-8328</identifier><identifier>EISSN: 1558-0806</identifier><identifier>DOI: 10.1109/TCSI.2013.2284188</identifier><identifier>CODEN: ITCSCH</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Application specific integrated circuits ; Bandwidth ; Distance learning ; Feature extraction ; High definition video ; Learning ; Learning (artificial intelligence) ; Mathematical models ; Microprocessors ; network-on-chip ; Object recognition ; Portability ; Reinforcement ; reinforcement learning ; Streaming media</subject><ispartof>IEEE transactions on circuits and systems. I, Regular papers, 2014-02, Vol.61 (2), p.476-484</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Feb 2014</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c326t-93e3406e70a3dda29c395a7a32b173e8127973de6f4e9ef5b1a32ff18f4c3ec43</citedby><cites>FETCH-LOGICAL-c326t-93e3406e70a3dda29c395a7a32b173e8127973de6f4e9ef5b1a32ff18f4c3ec43</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6642153$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6642153$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Park, Junyoung</creatorcontrib><creatorcontrib>Hong, Injoon</creatorcontrib><creatorcontrib>Kim, Gyeonghoon</creatorcontrib><creatorcontrib>Nam, Byeong-Gyu</creatorcontrib><creatorcontrib>Yoo, Hoi-Jun</creatorcontrib><title>Intelligent Network-on-Chip With Online Reinforcement Learning for Portable HD Object Recognition Processor</title><title>IEEE transactions on circuits and systems. I, Regular papers</title><addtitle>TCSI</addtitle><description>An intelligent Reinforcement Learning (RL) Network-on-Chip (NoC) is proposed as a communication architecture of a heterogeneous many-core processor for portable HD object recognition. The proposed RL NoC automatically learns bandwidth adjustment and resource allocation in the heterogeneous many-core processor without explicit modeling. By regulating the bandwidth and reallocating cores, the throughput performances of feature detection and description are increased by 20.4% and 11.5%, respectively. As a result, the overall execution time of the object recognition is reduced by 38%. The proposed processor with RL NoC is implemented in a 65 nm CMOS process, and it successfully demonstrates the real-time object recognition for a 720 p HD video stream while consuming 235 mW peak power at 200 MHz, 1.2 V.</description><subject>Application specific integrated circuits</subject><subject>Bandwidth</subject><subject>Distance learning</subject><subject>Feature extraction</subject><subject>High definition video</subject><subject>Learning</subject><subject>Learning (artificial intelligence)</subject><subject>Mathematical models</subject><subject>Microprocessors</subject><subject>network-on-chip</subject><subject>Object recognition</subject><subject>Portability</subject><subject>Reinforcement</subject><subject>reinforcement learning</subject><subject>Streaming media</subject><issn>1549-8328</issn><issn>1558-0806</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2014</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpdkMFqGzEQQJfSQN20H1B6EeSSyzoaSbsrHYvTNgZTm8SlRyHLs7bsteRIMqF_n11scshphpk3w8wrim9AxwBU3S0nT9Mxo8DHjEkBUn4oRlBVsqSS1h-HXKhSciY_FZ9T2lHKFOUwKvZTn7Hr3AZ9Jn8wv4S4L4MvJ1t3JP9c3pK575xH8ojOtyFaPAzkDE30zm9IXyKLELNZdUge7sl8tUObe9qGjXfZBU8WMVhMKcQvxVVruoRfL_G6-Pvr53LyUM7mv6eTH7PSclbnUnHkgtbYUMPXa8OU5aoyjeFsBQ1HCaxRDV9j3QpU2FYr6FttC7IVlqMV_Lq4Pe89xvB8wpT1wSXbf2k8hlPSUMuqaYQSrEdv3qG7cIq-v05DRUUNEvhAwZmyMaQUsdXH6A4m_tdA9aBfD_r1oF9f9Pcz388zDhHf-LoWDCrOXwHz2IFM</recordid><startdate>20140201</startdate><enddate>20140201</enddate><creator>Park, Junyoung</creator><creator>Hong, Injoon</creator><creator>Kim, Gyeonghoon</creator><creator>Nam, Byeong-Gyu</creator><creator>Yoo, Hoi-Jun</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>L7M</scope><scope>7SC</scope><scope>F28</scope><scope>FR3</scope><scope>JQ2</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20140201</creationdate><title>Intelligent Network-on-Chip With Online Reinforcement Learning for Portable HD Object Recognition Processor</title><author>Park, Junyoung ; Hong, Injoon ; Kim, Gyeonghoon ; Nam, Byeong-Gyu ; Yoo, Hoi-Jun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c326t-93e3406e70a3dda29c395a7a32b173e8127973de6f4e9ef5b1a32ff18f4c3ec43</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Application specific integrated circuits</topic><topic>Bandwidth</topic><topic>Distance learning</topic><topic>Feature extraction</topic><topic>High definition video</topic><topic>Learning</topic><topic>Learning (artificial intelligence)</topic><topic>Mathematical models</topic><topic>Microprocessors</topic><topic>network-on-chip</topic><topic>Object recognition</topic><topic>Portability</topic><topic>Reinforcement</topic><topic>reinforcement learning</topic><topic>Streaming media</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Park, Junyoung</creatorcontrib><creatorcontrib>Hong, Injoon</creatorcontrib><creatorcontrib>Kim, Gyeonghoon</creatorcontrib><creatorcontrib>Nam, Byeong-Gyu</creatorcontrib><creatorcontrib>Yoo, Hoi-Jun</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE transactions on circuits and systems. I, Regular papers</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Park, Junyoung</au><au>Hong, Injoon</au><au>Kim, Gyeonghoon</au><au>Nam, Byeong-Gyu</au><au>Yoo, Hoi-Jun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Intelligent Network-on-Chip With Online Reinforcement Learning for Portable HD Object Recognition Processor</atitle><jtitle>IEEE transactions on circuits and systems. I, Regular papers</jtitle><stitle>TCSI</stitle><date>2014-02-01</date><risdate>2014</risdate><volume>61</volume><issue>2</issue><spage>476</spage><epage>484</epage><pages>476-484</pages><issn>1549-8328</issn><eissn>1558-0806</eissn><coden>ITCSCH</coden><abstract>An intelligent Reinforcement Learning (RL) Network-on-Chip (NoC) is proposed as a communication architecture of a heterogeneous many-core processor for portable HD object recognition. The proposed RL NoC automatically learns bandwidth adjustment and resource allocation in the heterogeneous many-core processor without explicit modeling. By regulating the bandwidth and reallocating cores, the throughput performances of feature detection and description are increased by 20.4% and 11.5%, respectively. As a result, the overall execution time of the object recognition is reduced by 38%. The proposed processor with RL NoC is implemented in a 65 nm CMOS process, and it successfully demonstrates the real-time object recognition for a 720 p HD video stream while consuming 235 mW peak power at 200 MHz, 1.2 V.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TCSI.2013.2284188</doi><tpages>9</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1549-8328 |
| ispartof | IEEE transactions on circuits and systems. I, Regular papers, 2014-02, Vol.61 (2), p.476-484 |
| issn | 1549-8328 1558-0806 |
| language | eng |
| recordid | cdi_crossref_primary_10_1109_TCSI_2013_2284188 |
| source | IEEE Electronic Library (IEL) |
| subjects | Application specific integrated circuits Bandwidth Distance learning Feature extraction High definition video Learning Learning (artificial intelligence) Mathematical models Microprocessors network-on-chip Object recognition Portability Reinforcement reinforcement learning Streaming media |
| title | Intelligent Network-on-Chip With Online Reinforcement Learning for Portable HD Object Recognition Processor |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T10%3A38%3A05IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Intelligent%20Network-on-Chip%20With%20Online%20Reinforcement%20Learning%20for%20Portable%20HD%20Object%20Recognition%20Processor&rft.jtitle=IEEE%20transactions%20on%20circuits%20and%20systems.%20I,%20Regular%20papers&rft.au=Park,%20Junyoung&rft.date=2014-02-01&rft.volume=61&rft.issue=2&rft.spage=476&rft.epage=484&rft.pages=476-484&rft.issn=1549-8328&rft.eissn=1558-0806&rft.coden=ITCSCH&rft_id=info:doi/10.1109/TCSI.2013.2284188&rft_dat=%3Cproquest_RIE%3E3238314441%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1504618132&rft_id=info:pmid/&rft_ieee_id=6642153&rfr_iscdi=true |