Statistical mechanics of lossy compression for non-monotonic multilayer perceptrons

A lossy data compression scheme for uniformly biased Boolean messages is investigated via statistical mechanics techniques. The present paper utilize tree-like committee machine (committee tree) and tree-like parity machine (parity tree) whose transfer functions are non-monotonic, completing the stu...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cousseau, F., Mimura, K., Okada, M.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 513
container_issue
container_start_page 509
container_title
container_volume
creator Cousseau, F.
Mimura, K.
Okada, M.
description A lossy data compression scheme for uniformly biased Boolean messages is investigated via statistical mechanics techniques. The present paper utilize tree-like committee machine (committee tree) and tree-like parity machine (parity tree) whose transfer functions are non-monotonic, completing the study of the lossy compression scheme using perceptron-based decoder. The scheme performance at the infinite code length limit is analyzed using the replica method. Both committee and parity treelike networks are shown to saturate the Shannon bound.
doi_str_mv 10.1109/ISIT.2008.4595038
format Conference Proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4595038</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4595038</ieee_id><sourcerecordid>4595038</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-d7e1a6e667fe78daf4516d3ecf339a0ef592ba7ef7cf08afbdcafbd0e8c35f073</originalsourceid><addsrcrecordid>eNpVkLtOAzEURM0jElHIByAa_8AGP_faJYp4rBSJIqGOHO-1MNpdr9amyN8TRCiYYqY4oymGkDvOVpwz-9Bsm91KMGZWSlvNpLkgSwuGK6GUEBrsJZkLrqEynMPVP1aL6z_GrJ6ROYiKg1USbsgy5092ktJSKDMn221xJeYSvetoj_7DDdFnmgLtUs5H6lM_TphzTAMNaaJDGqo-DamkU4_2X12JnTviREecPI5lSkO-JbPguozLcy7I-_PTbv1abd5emvXjpoocdKlaQO5qrGsICKZ1QWletxJ9kNI6hkFbcXCAAXxgxoVD63-MofFSBwZyQe5_dyMi7scp9m467s93yW_PTlsk</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Statistical mechanics of lossy compression for non-monotonic multilayer perceptrons</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Cousseau, F. ; Mimura, K. ; Okada, M.</creator><creatorcontrib>Cousseau, F. ; Mimura, K. ; Okada, M.</creatorcontrib><description>A lossy data compression scheme for uniformly biased Boolean messages is investigated via statistical mechanics techniques. The present paper utilize tree-like committee machine (committee tree) and tree-like parity machine (parity tree) whose transfer functions are non-monotonic, completing the study of the lossy compression scheme using perceptron-based decoder. The scheme performance at the infinite code length limit is analyzed using the replica method. Both committee and parity treelike networks are shown to saturate the Shannon bound.</description><identifier>ISSN: 2157-8095</identifier><identifier>ISBN: 9781424422562</identifier><identifier>ISBN: 1424422566</identifier><identifier>EISSN: 2157-8117</identifier><identifier>EISBN: 9781424422579</identifier><identifier>EISBN: 1424422574</identifier><identifier>DOI: 10.1109/ISIT.2008.4595038</identifier><identifier>LCCN: 72-179437</identifier><language>eng</language><publisher>IEEE</publisher><subject>Decoding ; Equations ; Mathematical model ; Multilayer perceptrons ; Rate-distortion ; Stability analysis ; Stability criteria</subject><ispartof>2008 IEEE International Symposium on Information Theory, 2008, p.509-513</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4595038$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,27904,54898</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4595038$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Cousseau, F.</creatorcontrib><creatorcontrib>Mimura, K.</creatorcontrib><creatorcontrib>Okada, M.</creatorcontrib><title>Statistical mechanics of lossy compression for non-monotonic multilayer perceptrons</title><title>2008 IEEE International Symposium on Information Theory</title><addtitle>ISIT</addtitle><description>A lossy data compression scheme for uniformly biased Boolean messages is investigated via statistical mechanics techniques. The present paper utilize tree-like committee machine (committee tree) and tree-like parity machine (parity tree) whose transfer functions are non-monotonic, completing the study of the lossy compression scheme using perceptron-based decoder. The scheme performance at the infinite code length limit is analyzed using the replica method. Both committee and parity treelike networks are shown to saturate the Shannon bound.</description><subject>Decoding</subject><subject>Equations</subject><subject>Mathematical model</subject><subject>Multilayer perceptrons</subject><subject>Rate-distortion</subject><subject>Stability analysis</subject><subject>Stability criteria</subject><issn>2157-8095</issn><issn>2157-8117</issn><isbn>9781424422562</isbn><isbn>1424422566</isbn><isbn>9781424422579</isbn><isbn>1424422574</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2008</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpVkLtOAzEURM0jElHIByAa_8AGP_faJYp4rBSJIqGOHO-1MNpdr9amyN8TRCiYYqY4oymGkDvOVpwz-9Bsm91KMGZWSlvNpLkgSwuGK6GUEBrsJZkLrqEynMPVP1aL6z_GrJ6ROYiKg1USbsgy5092ktJSKDMn221xJeYSvetoj_7DDdFnmgLtUs5H6lM_TphzTAMNaaJDGqo-DamkU4_2X12JnTviREecPI5lSkO-JbPguozLcy7I-_PTbv1abd5emvXjpoocdKlaQO5qrGsICKZ1QWletxJ9kNI6hkFbcXCAAXxgxoVD63-MofFSBwZyQe5_dyMi7scp9m467s93yW_PTlsk</recordid><startdate>200807</startdate><enddate>200807</enddate><creator>Cousseau, F.</creator><creator>Mimura, K.</creator><creator>Okada, M.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>200807</creationdate><title>Statistical mechanics of lossy compression for non-monotonic multilayer perceptrons</title><author>Cousseau, F. ; Mimura, K. ; Okada, M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-d7e1a6e667fe78daf4516d3ecf339a0ef592ba7ef7cf08afbdcafbd0e8c35f073</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Decoding</topic><topic>Equations</topic><topic>Mathematical model</topic><topic>Multilayer perceptrons</topic><topic>Rate-distortion</topic><topic>Stability analysis</topic><topic>Stability criteria</topic><toplevel>online_resources</toplevel><creatorcontrib>Cousseau, F.</creatorcontrib><creatorcontrib>Mimura, K.</creatorcontrib><creatorcontrib>Okada, M.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Cousseau, F.</au><au>Mimura, K.</au><au>Okada, M.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Statistical mechanics of lossy compression for non-monotonic multilayer perceptrons</atitle><btitle>2008 IEEE International Symposium on Information Theory</btitle><stitle>ISIT</stitle><date>2008-07</date><risdate>2008</risdate><spage>509</spage><epage>513</epage><pages>509-513</pages><issn>2157-8095</issn><eissn>2157-8117</eissn><isbn>9781424422562</isbn><isbn>1424422566</isbn><eisbn>9781424422579</eisbn><eisbn>1424422574</eisbn><abstract>A lossy data compression scheme for uniformly biased Boolean messages is investigated via statistical mechanics techniques. The present paper utilize tree-like committee machine (committee tree) and tree-like parity machine (parity tree) whose transfer functions are non-monotonic, completing the study of the lossy compression scheme using perceptron-based decoder. The scheme performance at the infinite code length limit is analyzed using the replica method. Both committee and parity treelike networks are shown to saturate the Shannon bound.</abstract><pub>IEEE</pub><doi>10.1109/ISIT.2008.4595038</doi><tpages>5</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 2157-8095
ispartof 2008 IEEE International Symposium on Information Theory, 2008, p.509-513
issn 2157-8095
2157-8117
language eng
recordid cdi_ieee_primary_4595038
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Decoding
Equations
Mathematical model
Multilayer perceptrons
Rate-distortion
Stability analysis
Stability criteria
title Statistical mechanics of lossy compression for non-monotonic multilayer perceptrons
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T18%3A56%3A22IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Statistical%20mechanics%20of%20lossy%20compression%20for%20non-monotonic%20multilayer%20perceptrons&rft.btitle=2008%20IEEE%20International%20Symposium%20on%20Information%20Theory&rft.au=Cousseau,%20F.&rft.date=2008-07&rft.spage=509&rft.epage=513&rft.pages=509-513&rft.issn=2157-8095&rft.eissn=2157-8117&rft.isbn=9781424422562&rft.isbn_list=1424422566&rft_id=info:doi/10.1109/ISIT.2008.4595038&rft_dat=%3Cieee_6IE%3E4595038%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781424422579&rft.eisbn_list=1424422574&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4595038&rfr_iscdi=true