Hybrid Quaternionic Hopfield Neural Network
In recent years, applications of complex-valued neural networks have become wide spread. Quaternions are an extension of complex numbers, and neural networks with quaternions have been proposed. Because quaternion algebra is non-commutative algebra, we can consider two orders of multiplication to ca...
Gespeichert in:
| Veröffentlicht in: | IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences Communications and Computer Sciences, 2015/07/01, Vol.E98.A(7), pp.1512-1518 |
|---|---|
| 1. Verfasser: | |
| Format: | Artikel |
| Sprache: | eng ; jpn |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1518 |
|---|---|
| container_issue | 7 |
| container_start_page | 1512 |
| container_title | IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences |
| container_volume | E98.A |
| creator | KOBAYASHI, Masaki |
| description | In recent years, applications of complex-valued neural networks have become wide spread. Quaternions are an extension of complex numbers, and neural networks with quaternions have been proposed. Because quaternion algebra is non-commutative algebra, we can consider two orders of multiplication to calculate weighted input. However, both orders provide almost the same performance. We propose hybrid quaternionic Hopfield neural networks, which have both orders of multiplication. Using computer simulations, we show that these networks outperformed conventional quaternionic Hopfield neural networks in noise tolerance. We discuss why hybrid quaternionic Hopfield neural networks improve noise tolerance from the standpoint of rotational invariance. |
| doi_str_mv | 10.1587/transfun.E98.A.1512 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1823941047</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1823941047</sourcerecordid><originalsourceid>FETCH-LOGICAL-c548t-2459cc35f0d45de4323e0ac7dc8e980d3ec1138f6abcaf4b9c0b2525ccf54803</originalsourceid><addsrcrecordid>eNqFkMFKAzEQQIMoWKtf4KVHQbYmm6RJjqVUWyiK0HvIzk5063a3JlnEv3dLtYgXTwPDe8PwCLlmdMykVncpuCb6rhnPjR5P-x3LT8iAKSEzxrk6JQNq2CTTkupzchHjhlKmcyYG5HbxWYSqHD13LmFoqrapYLRod77Cuhw9Yhdc3Y_00Ya3S3LmXR3x6nsOyfp-vp4tstXTw3I2XWUghU5ZLqQB4NLTUsgSBc85UgeqBI1G05IjMMa1n7gCnBeFAVrkMpcAvvcpH5Kbw9ldaN87jMluqwhY167Btou2_5wbwahQ_6OKaSMmWsoe5QcUQhtjQG93odq68GkZtfuI9iei7SPaqd1H7K3lwdrE5F7w6LiQKqjxr6N-uUcGXl2w2PAvk_GCCA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1718946855</pqid></control><display><type>article</type><title>Hybrid Quaternionic Hopfield Neural Network</title><source>J-STAGE (Japan Science & Technology Information Aggregator, Electronic) Freely Available Titles - Japanese</source><creator>KOBAYASHI, Masaki</creator><creatorcontrib>KOBAYASHI, Masaki</creatorcontrib><description>In recent years, applications of complex-valued neural networks have become wide spread. Quaternions are an extension of complex numbers, and neural networks with quaternions have been proposed. Because quaternion algebra is non-commutative algebra, we can consider two orders of multiplication to calculate weighted input. However, both orders provide almost the same performance. We propose hybrid quaternionic Hopfield neural networks, which have both orders of multiplication. Using computer simulations, we show that these networks outperformed conventional quaternionic Hopfield neural networks in noise tolerance. We discuss why hybrid quaternionic Hopfield neural networks improve noise tolerance from the standpoint of rotational invariance.</description><identifier>ISSN: 0916-8508</identifier><identifier>EISSN: 1745-1337</identifier><identifier>DOI: 10.1587/transfun.E98.A.1512</identifier><language>eng ; jpn</language><publisher>The Institute of Electronics, Information and Communication Engineers</publisher><subject>Algebra ; complex-valued associative memory ; Computer simulation ; Hopfield neural networks ; Mathematical analysis ; Multiplication ; Neural networks ; Noise tolerance ; quaternion ; Quaternions ; rotational invariance ; Spreads</subject><ispartof>IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2015/07/01, Vol.E98.A(7), pp.1512-1518</ispartof><rights>2015 The Institute of Electronics, Information and Communication Engineers</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c548t-2459cc35f0d45de4323e0ac7dc8e980d3ec1138f6abcaf4b9c0b2525ccf54803</citedby><cites>FETCH-LOGICAL-c548t-2459cc35f0d45de4323e0ac7dc8e980d3ec1138f6abcaf4b9c0b2525ccf54803</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,1882,4023,27922,27923,27924</link.rule.ids></links><search><creatorcontrib>KOBAYASHI, Masaki</creatorcontrib><title>Hybrid Quaternionic Hopfield Neural Network</title><title>IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences</title><addtitle>IEICE Trans. Fundamentals</addtitle><description>In recent years, applications of complex-valued neural networks have become wide spread. Quaternions are an extension of complex numbers, and neural networks with quaternions have been proposed. Because quaternion algebra is non-commutative algebra, we can consider two orders of multiplication to calculate weighted input. However, both orders provide almost the same performance. We propose hybrid quaternionic Hopfield neural networks, which have both orders of multiplication. Using computer simulations, we show that these networks outperformed conventional quaternionic Hopfield neural networks in noise tolerance. We discuss why hybrid quaternionic Hopfield neural networks improve noise tolerance from the standpoint of rotational invariance.</description><subject>Algebra</subject><subject>complex-valued associative memory</subject><subject>Computer simulation</subject><subject>Hopfield neural networks</subject><subject>Mathematical analysis</subject><subject>Multiplication</subject><subject>Neural networks</subject><subject>Noise tolerance</subject><subject>quaternion</subject><subject>Quaternions</subject><subject>rotational invariance</subject><subject>Spreads</subject><issn>0916-8508</issn><issn>1745-1337</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2015</creationdate><recordtype>article</recordtype><recordid>eNqFkMFKAzEQQIMoWKtf4KVHQbYmm6RJjqVUWyiK0HvIzk5063a3JlnEv3dLtYgXTwPDe8PwCLlmdMykVncpuCb6rhnPjR5P-x3LT8iAKSEzxrk6JQNq2CTTkupzchHjhlKmcyYG5HbxWYSqHD13LmFoqrapYLRod77Cuhw9Yhdc3Y_00Ya3S3LmXR3x6nsOyfp-vp4tstXTw3I2XWUghU5ZLqQB4NLTUsgSBc85UgeqBI1G05IjMMa1n7gCnBeFAVrkMpcAvvcpH5Kbw9ldaN87jMluqwhY167Btou2_5wbwahQ_6OKaSMmWsoe5QcUQhtjQG93odq68GkZtfuI9iei7SPaqd1H7K3lwdrE5F7w6LiQKqjxr6N-uUcGXl2w2PAvk_GCCA</recordid><startdate>2015</startdate><enddate>2015</enddate><creator>KOBAYASHI, Masaki</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><scope>7QO</scope><scope>FR3</scope><scope>P64</scope></search><sort><creationdate>2015</creationdate><title>Hybrid Quaternionic Hopfield Neural Network</title><author>KOBAYASHI, Masaki</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c548t-2459cc35f0d45de4323e0ac7dc8e980d3ec1138f6abcaf4b9c0b2525ccf54803</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng ; jpn</language><creationdate>2015</creationdate><topic>Algebra</topic><topic>complex-valued associative memory</topic><topic>Computer simulation</topic><topic>Hopfield neural networks</topic><topic>Mathematical analysis</topic><topic>Multiplication</topic><topic>Neural networks</topic><topic>Noise tolerance</topic><topic>quaternion</topic><topic>Quaternions</topic><topic>rotational invariance</topic><topic>Spreads</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>KOBAYASHI, Masaki</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><collection>Biotechnology Research Abstracts</collection><collection>Engineering Research Database</collection><collection>Biotechnology and BioEngineering Abstracts</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>KOBAYASHI, Masaki</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Hybrid Quaternionic Hopfield Neural Network</atitle><jtitle>IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences</jtitle><addtitle>IEICE Trans. Fundamentals</addtitle><date>2015</date><risdate>2015</risdate><volume>E98.A</volume><issue>7</issue><spage>1512</spage><epage>1518</epage><pages>1512-1518</pages><issn>0916-8508</issn><eissn>1745-1337</eissn><abstract>In recent years, applications of complex-valued neural networks have become wide spread. Quaternions are an extension of complex numbers, and neural networks with quaternions have been proposed. Because quaternion algebra is non-commutative algebra, we can consider two orders of multiplication to calculate weighted input. However, both orders provide almost the same performance. We propose hybrid quaternionic Hopfield neural networks, which have both orders of multiplication. Using computer simulations, we show that these networks outperformed conventional quaternionic Hopfield neural networks in noise tolerance. We discuss why hybrid quaternionic Hopfield neural networks improve noise tolerance from the standpoint of rotational invariance.</abstract><pub>The Institute of Electronics, Information and Communication Engineers</pub><doi>10.1587/transfun.E98.A.1512</doi><tpages>7</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0916-8508 |
| ispartof | IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2015/07/01, Vol.E98.A(7), pp.1512-1518 |
| issn | 0916-8508 1745-1337 |
| language | eng ; jpn |
| recordid | cdi_proquest_miscellaneous_1823941047 |
| source | J-STAGE (Japan Science & Technology Information Aggregator, Electronic) Freely Available Titles - Japanese |
| subjects | Algebra complex-valued associative memory Computer simulation Hopfield neural networks Mathematical analysis Multiplication Neural networks Noise tolerance quaternion Quaternions rotational invariance Spreads |
| title | Hybrid Quaternionic Hopfield Neural Network |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T18%3A17%3A05IST&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=Hybrid%20Quaternionic%20Hopfield%20Neural%20Network&rft.jtitle=IEICE%20Transactions%20on%20Fundamentals%20of%20Electronics,%20Communications%20and%20Computer%20Sciences&rft.au=KOBAYASHI,%20Masaki&rft.date=2015&rft.volume=E98.A&rft.issue=7&rft.spage=1512&rft.epage=1518&rft.pages=1512-1518&rft.issn=0916-8508&rft.eissn=1745-1337&rft_id=info:doi/10.1587/transfun.E98.A.1512&rft_dat=%3Cproquest_cross%3E1823941047%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=1718946855&rft_id=info:pmid/&rfr_iscdi=true |