Sparsification and Stability of Simple Dynamic Binary Neural Networks
This letter studies the simple dynamic binary neural network characterized by signum activation function and ternary connection parameters. In order to control the sparsity of the connections and the stability of the stored signal, a simple evolutionary algorithm is presented. As a basic example of...
Gespeichert in:
| Veröffentlicht in: | IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences Communications and Computer Sciences, 2014/04/01, Vol.E97.A(4), pp.985-988 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 988 |
|---|---|
| container_issue | 4 |
| container_start_page | 985 |
| container_title | IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences |
| container_volume | E97.A |
| creator | MORIYASU, Jungo SAITO, Toshimichi |
| description | This letter studies the simple dynamic binary neural network characterized by signum activation function and ternary connection parameters. In order to control the sparsity of the connections and the stability of the stored signal, a simple evolutionary algorithm is presented. As a basic example of teacher signals, we consider a binary periodic orbit which corresponds to a control signal of ac-dc regulators. In the numerical experiment, applying the correlation-based learning, the periodic orbit can be stored. The sparsification can be effective to reinforce the stability of the periodic orbit. |
| doi_str_mv | 10.1587/transfun.E97.A.985 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1541425557</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1541425557</sourcerecordid><originalsourceid>FETCH-LOGICAL-c512t-c50e0714e72dc39118cff86f8cd2c9b809d47651cfe6fd81fbca13eef2812c8f3</originalsourceid><addsrcrecordid>eNpdkLFOwzAURS0EEqXwA0wZWRL8nDh2xlIKRapgKMyW69jgkjjBdoT69wQVisTy7nLP1dNB6BJwBpSz6-ilC2Zw2aJi2SyrOD1CE2AFTSHP2TGa4ArKlFPMT9FZCFuMgRMoJmix7qUP1lglo-1cIl2drKPc2MbGXdKZZG3bvtHJ7c7J1qrkxjrpd8mjHrxsxoifnX8P5-jEyCboi5-cope7xfN8ma6e7h_ms1WqKJA4Xqwxg0IzUqu8AuDKGF4armqiqg3HVV2wkoIyujQ1B7NREnKtDeFAFDf5FF3td3vffQw6RNHaoHTTSKe7IQigBRSEUsrGKtlXle9C8NqI3tt2_F0AFt_OxK8zMToTMzE6G6HlHtqGKF_1AZE-WtXo_0jxhx4q6k16oV3-Bafkfec</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1541425557</pqid></control><display><type>article</type><title>Sparsification and Stability of Simple Dynamic Binary Neural Networks</title><source>J-STAGE Free</source><creator>MORIYASU, Jungo ; SAITO, Toshimichi</creator><creatorcontrib>MORIYASU, Jungo ; SAITO, Toshimichi</creatorcontrib><description>This letter studies the simple dynamic binary neural network characterized by signum activation function and ternary connection parameters. In order to control the sparsity of the connections and the stability of the stored signal, a simple evolutionary algorithm is presented. As a basic example of teacher signals, we consider a binary periodic orbit which corresponds to a control signal of ac-dc regulators. In the numerical experiment, applying the correlation-based learning, the periodic orbit can be stored. The sparsification can be effective to reinforce the stability of the periodic orbit.</description><identifier>ISSN: 0916-8508</identifier><identifier>EISSN: 1745-1337</identifier><identifier>DOI: 10.1587/transfun.E97.A.985</identifier><language>eng</language><publisher>The Institute of Electronics, Information and Communication Engineers</publisher><subject>Dynamic tests ; Dynamics ; Joints ; Mathematical models ; multi-layer perceptron ; Neural networks ; Orbits ; Stability ; supervised learning ; switching power converters ; Teachers</subject><ispartof>IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2014/04/01, Vol.E97.A(4), pp.985-988</ispartof><rights>2014 The Institute of Electronics, Information and Communication Engineers</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c512t-c50e0714e72dc39118cff86f8cd2c9b809d47651cfe6fd81fbca13eef2812c8f3</citedby><cites>FETCH-LOGICAL-c512t-c50e0714e72dc39118cff86f8cd2c9b809d47651cfe6fd81fbca13eef2812c8f3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,1877,4010,27900,27901,27902</link.rule.ids></links><search><creatorcontrib>MORIYASU, Jungo</creatorcontrib><creatorcontrib>SAITO, Toshimichi</creatorcontrib><title>Sparsification and Stability of Simple Dynamic Binary Neural Networks</title><title>IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences</title><addtitle>IEICE Trans. Fundamentals</addtitle><description>This letter studies the simple dynamic binary neural network characterized by signum activation function and ternary connection parameters. In order to control the sparsity of the connections and the stability of the stored signal, a simple evolutionary algorithm is presented. As a basic example of teacher signals, we consider a binary periodic orbit which corresponds to a control signal of ac-dc regulators. In the numerical experiment, applying the correlation-based learning, the periodic orbit can be stored. The sparsification can be effective to reinforce the stability of the periodic orbit.</description><subject>Dynamic tests</subject><subject>Dynamics</subject><subject>Joints</subject><subject>Mathematical models</subject><subject>multi-layer perceptron</subject><subject>Neural networks</subject><subject>Orbits</subject><subject>Stability</subject><subject>supervised learning</subject><subject>switching power converters</subject><subject>Teachers</subject><issn>0916-8508</issn><issn>1745-1337</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2014</creationdate><recordtype>article</recordtype><recordid>eNpdkLFOwzAURS0EEqXwA0wZWRL8nDh2xlIKRapgKMyW69jgkjjBdoT69wQVisTy7nLP1dNB6BJwBpSz6-ilC2Zw2aJi2SyrOD1CE2AFTSHP2TGa4ArKlFPMT9FZCFuMgRMoJmix7qUP1lglo-1cIl2drKPc2MbGXdKZZG3bvtHJ7c7J1qrkxjrpd8mjHrxsxoifnX8P5-jEyCboi5-cope7xfN8ma6e7h_ms1WqKJA4Xqwxg0IzUqu8AuDKGF4armqiqg3HVV2wkoIyujQ1B7NREnKtDeFAFDf5FF3td3vffQw6RNHaoHTTSKe7IQigBRSEUsrGKtlXle9C8NqI3tt2_F0AFt_OxK8zMToTMzE6G6HlHtqGKF_1AZE-WtXo_0jxhx4q6k16oV3-Bafkfec</recordid><startdate>2014</startdate><enddate>2014</enddate><creator>MORIYASU, Jungo</creator><creator>SAITO, Toshimichi</creator><general>The Institute of Electronics, Information and Communication Engineers</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>2014</creationdate><title>Sparsification and Stability of Simple Dynamic Binary Neural Networks</title><author>MORIYASU, Jungo ; SAITO, Toshimichi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c512t-c50e0714e72dc39118cff86f8cd2c9b809d47651cfe6fd81fbca13eef2812c8f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Dynamic tests</topic><topic>Dynamics</topic><topic>Joints</topic><topic>Mathematical models</topic><topic>multi-layer perceptron</topic><topic>Neural networks</topic><topic>Orbits</topic><topic>Stability</topic><topic>supervised learning</topic><topic>switching power converters</topic><topic>Teachers</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>MORIYASU, Jungo</creatorcontrib><creatorcontrib>SAITO, Toshimichi</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>MORIYASU, Jungo</au><au>SAITO, Toshimichi</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Sparsification and Stability of Simple Dynamic Binary Neural Networks</atitle><jtitle>IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences</jtitle><addtitle>IEICE Trans. Fundamentals</addtitle><date>2014</date><risdate>2014</risdate><volume>E97.A</volume><issue>4</issue><spage>985</spage><epage>988</epage><pages>985-988</pages><issn>0916-8508</issn><eissn>1745-1337</eissn><abstract>This letter studies the simple dynamic binary neural network characterized by signum activation function and ternary connection parameters. In order to control the sparsity of the connections and the stability of the stored signal, a simple evolutionary algorithm is presented. As a basic example of teacher signals, we consider a binary periodic orbit which corresponds to a control signal of ac-dc regulators. In the numerical experiment, applying the correlation-based learning, the periodic orbit can be stored. The sparsification can be effective to reinforce the stability of the periodic orbit.</abstract><pub>The Institute of Electronics, Information and Communication Engineers</pub><doi>10.1587/transfun.E97.A.985</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0916-8508 |
| ispartof | IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2014/04/01, Vol.E97.A(4), pp.985-988 |
| issn | 0916-8508 1745-1337 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_1541425557 |
| source | J-STAGE Free |
| subjects | Dynamic tests Dynamics Joints Mathematical models multi-layer perceptron Neural networks Orbits Stability supervised learning switching power converters Teachers |
| title | Sparsification and Stability of Simple Dynamic Binary Neural Networks |
| 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%3A08%3A29IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Sparsification%20and%20Stability%20of%20Simple%20Dynamic%20Binary%20Neural%20Networks&rft.jtitle=IEICE%20Transactions%20on%20Fundamentals%20of%20Electronics,%20Communications%20and%20Computer%20Sciences&rft.au=MORIYASU,%20Jungo&rft.date=2014&rft.volume=E97.A&rft.issue=4&rft.spage=985&rft.epage=988&rft.pages=985-988&rft.issn=0916-8508&rft.eissn=1745-1337&rft_id=info:doi/10.1587/transfun.E97.A.985&rft_dat=%3Cproquest_cross%3E1541425557%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1541425557&rft_id=info:pmid/&rfr_iscdi=true |