Dynamic binary neural networks and storage of control signals for switching circuits

This paper studies basic dynamics and learning capability of the simple dynamic binary neural network. The network has the signum activation function and can exhibit various binary periodic orbits. In order to visualize the dynamics, we introduce the Gray-code-based return map. In order to store a d...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Moriyasu, J., Kouzuki, R., Saito, T.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 494
container_issue
container_start_page 491
container_title
container_volume
creator Moriyasu, J.
Kouzuki, R.
Saito, T.
description This paper studies basic dynamics and learning capability of the simple dynamic binary neural network. The network has the signum activation function and can exhibit various binary periodic orbits. In order to visualize the dynamics, we introduce the Gray-code-based return map. In order to store a desired binary periodic orbit, we present a simple learning algorithm based on the correlation learning. We then try to store a teacher signal corresponding to a typical control signal of a switching power converter. Performing numerical experiments, we have confirmed the storage of the teacher signal and its automatic stabilization.
doi_str_mv 10.1109/APCCAS.2012.6419079
format Conference Proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6419079</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6419079</ieee_id><sourcerecordid>6419079</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-c3db472fe6eff556e4442f9a41f9ad0cd107a03a3edf2b0cd57f266073bea15f3</originalsourceid><addsrcrecordid>eNotj8tqwzAURNVFoW2SL8hGP2BXV896adwnBFpIug6yLLlqHalICiF_X0OzmcMwMHAQWgOpAUhz3350XbutKQFaSw4NUc0VugMulAJFm4cbtMr5mxACSkoG8hbtHs9BH7zBvQ86nXGwx6SnGeUU00_GOgw4l5j0aHF02MRQUpxw9mPQU8YuJpxPvpgvH0ZsfDJHX_ISXbt5tasLF-jz-WnXvVab95e3rt1UHpQolWFDzxV1VlrnhJCWc05doznMMRAzAFGaMM3s4Gg_d6EclZIo1lsNwrEFWv__emvt_jf5w6ywv4izPx06UTM</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Dynamic binary neural networks and storage of control signals for switching circuits</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Moriyasu, J. ; Kouzuki, R. ; Saito, T.</creator><creatorcontrib>Moriyasu, J. ; Kouzuki, R. ; Saito, T.</creatorcontrib><description>This paper studies basic dynamics and learning capability of the simple dynamic binary neural network. The network has the signum activation function and can exhibit various binary periodic orbits. In order to visualize the dynamics, we introduce the Gray-code-based return map. In order to store a desired binary periodic orbit, we present a simple learning algorithm based on the correlation learning. We then try to store a teacher signal corresponding to a typical control signal of a switching power converter. Performing numerical experiments, we have confirmed the storage of the teacher signal and its automatic stabilization.</description><identifier>EISBN: 1457717298</identifier><identifier>EISBN: 9781457717291</identifier><identifier>EISBN: 145771728X</identifier><identifier>EISBN: 9781457717284</identifier><identifier>DOI: 10.1109/APCCAS.2012.6419079</identifier><language>eng</language><publisher>IEEE</publisher><subject>Switches</subject><ispartof>2012 IEEE Asia Pacific Conference on Circuits and Systems, 2012, p.491-494</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/6419079$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6419079$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Moriyasu, J.</creatorcontrib><creatorcontrib>Kouzuki, R.</creatorcontrib><creatorcontrib>Saito, T.</creatorcontrib><title>Dynamic binary neural networks and storage of control signals for switching circuits</title><title>2012 IEEE Asia Pacific Conference on Circuits and Systems</title><addtitle>APCCAS</addtitle><description>This paper studies basic dynamics and learning capability of the simple dynamic binary neural network. The network has the signum activation function and can exhibit various binary periodic orbits. In order to visualize the dynamics, we introduce the Gray-code-based return map. In order to store a desired binary periodic orbit, we present a simple learning algorithm based on the correlation learning. We then try to store a teacher signal corresponding to a typical control signal of a switching power converter. Performing numerical experiments, we have confirmed the storage of the teacher signal and its automatic stabilization.</description><subject>Switches</subject><isbn>1457717298</isbn><isbn>9781457717291</isbn><isbn>145771728X</isbn><isbn>9781457717284</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2012</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotj8tqwzAURNVFoW2SL8hGP2BXV896adwnBFpIug6yLLlqHalICiF_X0OzmcMwMHAQWgOpAUhz3350XbutKQFaSw4NUc0VugMulAJFm4cbtMr5mxACSkoG8hbtHs9BH7zBvQ86nXGwx6SnGeUU00_GOgw4l5j0aHF02MRQUpxw9mPQU8YuJpxPvpgvH0ZsfDJHX_ISXbt5tasLF-jz-WnXvVab95e3rt1UHpQolWFDzxV1VlrnhJCWc05doznMMRAzAFGaMM3s4Gg_d6EclZIo1lsNwrEFWv__emvt_jf5w6ywv4izPx06UTM</recordid><startdate>201212</startdate><enddate>201212</enddate><creator>Moriyasu, J.</creator><creator>Kouzuki, R.</creator><creator>Saito, T.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201212</creationdate><title>Dynamic binary neural networks and storage of control signals for switching circuits</title><author>Moriyasu, J. ; Kouzuki, R. ; Saito, T.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-c3db472fe6eff556e4442f9a41f9ad0cd107a03a3edf2b0cd57f266073bea15f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Switches</topic><toplevel>online_resources</toplevel><creatorcontrib>Moriyasu, J.</creatorcontrib><creatorcontrib>Kouzuki, R.</creatorcontrib><creatorcontrib>Saito, T.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Moriyasu, J.</au><au>Kouzuki, R.</au><au>Saito, T.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Dynamic binary neural networks and storage of control signals for switching circuits</atitle><btitle>2012 IEEE Asia Pacific Conference on Circuits and Systems</btitle><stitle>APCCAS</stitle><date>2012-12</date><risdate>2012</risdate><spage>491</spage><epage>494</epage><pages>491-494</pages><eisbn>1457717298</eisbn><eisbn>9781457717291</eisbn><eisbn>145771728X</eisbn><eisbn>9781457717284</eisbn><abstract>This paper studies basic dynamics and learning capability of the simple dynamic binary neural network. The network has the signum activation function and can exhibit various binary periodic orbits. In order to visualize the dynamics, we introduce the Gray-code-based return map. In order to store a desired binary periodic orbit, we present a simple learning algorithm based on the correlation learning. We then try to store a teacher signal corresponding to a typical control signal of a switching power converter. Performing numerical experiments, we have confirmed the storage of the teacher signal and its automatic stabilization.</abstract><pub>IEEE</pub><doi>10.1109/APCCAS.2012.6419079</doi><tpages>4</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISBN: 1457717298
ispartof 2012 IEEE Asia Pacific Conference on Circuits and Systems, 2012, p.491-494
issn
language eng
recordid cdi_ieee_primary_6419079
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Switches
title Dynamic binary neural networks and storage of control signals for switching circuits
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-29T05%3A17%3A29IST&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=Dynamic%20binary%20neural%20networks%20and%20storage%20of%20control%20signals%20for%20switching%20circuits&rft.btitle=2012%20IEEE%20Asia%20Pacific%20Conference%20on%20Circuits%20and%20Systems&rft.au=Moriyasu,%20J.&rft.date=2012-12&rft.spage=491&rft.epage=494&rft.pages=491-494&rft_id=info:doi/10.1109/APCCAS.2012.6419079&rft_dat=%3Cieee_6IE%3E6419079%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1457717298&rft.eisbn_list=9781457717291&rft.eisbn_list=145771728X&rft.eisbn_list=9781457717284&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6419079&rfr_iscdi=true