A new design method for the complex-valued multistate Hopfield associative memory
A method to store each element of an integral memory set M /spl sub/ {1,2,...,K}/sup n/ as a fixed point into a complex-valued multistate Hopfield network is introduced. The method employs a set of inequalities to render each memory pattern as a strict local minimum of a quadratic energy landscape....
Gespeichert in:
| Veröffentlicht in: | IEEE transaction on neural networks and learning systems 2003-07, Vol.14 (4), p.891-899 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 899 |
|---|---|
| container_issue | 4 |
| container_start_page | 891 |
| container_title | IEEE transaction on neural networks and learning systems |
| container_volume | 14 |
| creator | Muezzinoglu, M.K. Guzelis, C. Zurada, J.M. |
| description | A method to store each element of an integral memory set M /spl sub/ {1,2,...,K}/sup n/ as a fixed point into a complex-valued multistate Hopfield network is introduced. The method employs a set of inequalities to render each memory pattern as a strict local minimum of a quadratic energy landscape. Based on the solution of this system, it gives a recurrent network of n multistate neurons with complex and symmetric synaptic weights, which operates on the finite state space {1,2,...,K}/sup n/ to minimize this quadratic functional. Maximum number of integral vectors that can be embedded into the energy landscape of the network by this method is investigated by computer experiments. This paper also enlightens the performance of the proposed method in reconstructing noisy gray-scale images. |
| doi_str_mv | 10.1109/TNN.2003.813844 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_1215405</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1215405</ieee_id><sourcerecordid>734249460</sourcerecordid><originalsourceid>FETCH-LOGICAL-c470t-58712f633f4c875181da6fea9d4af4593feb09700db556665468602ff15ef3e23</originalsourceid><addsrcrecordid>eNqF0c9rFTEQB_Agiq3VswdBggc97etMfudYitpCaSnUc8jbndgtuy_PzW61_31T3oOCBz1lIJ8ZmPky9h5hhQj--ObyciUA5MqhdEq9YIfoFTYAXr6sNSjdeCHsAXtTyh0AKg3mNTtAJ6QD4w7Z9Qnf0G_eUel_bvhI823ueMoTn2-Jt3ncDvSnuY_DQh0fl2Huyxxn4md5m3oaOh5LyW0f5_6eaveYp4e37FWKQ6F3-_eI_fj29eb0rLm4-n5-enLRtMrC3GhnUSQjZVKtsxoddtEkir5TMSntZaI1eAvQrbU2xmhlnAGREmpKkoQ8Yl92c7dT_rVQmcPYl5aGIW4oLyV4QIto5f-llUoorwxU-fmfUjhljXemwk9_wbu8TJu6b_ACnPH1zhUd71A75VImSmE79WOcHgJCeIov1PjCU3xhF1_t-Lgfu6xH6p79Pq8KPuxAT0TP3wK1Ai0fAQMdnHM</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>920869506</pqid></control><display><type>article</type><title>A new design method for the complex-valued multistate Hopfield associative memory</title><source>IEEE Electronic Library (IEL)</source><creator>Muezzinoglu, M.K. ; Guzelis, C. ; Zurada, J.M.</creator><creatorcontrib>Muezzinoglu, M.K. ; Guzelis, C. ; Zurada, J.M.</creatorcontrib><description>A method to store each element of an integral memory set M /spl sub/ {1,2,...,K}/sup n/ as a fixed point into a complex-valued multistate Hopfield network is introduced. The method employs a set of inequalities to render each memory pattern as a strict local minimum of a quadratic energy landscape. Based on the solution of this system, it gives a recurrent network of n multistate neurons with complex and symmetric synaptic weights, which operates on the finite state space {1,2,...,K}/sup n/ to minimize this quadratic functional. Maximum number of integral vectors that can be embedded into the energy landscape of the network by this method is investigated by computer experiments. This paper also enlightens the performance of the proposed method in reconstructing noisy gray-scale images.</description><identifier>ISSN: 1045-9227</identifier><identifier>ISSN: 2162-237X</identifier><identifier>EISSN: 1941-0093</identifier><identifier>EISSN: 2162-2388</identifier><identifier>DOI: 10.1109/TNN.2003.813844</identifier><identifier>PMID: 18238068</identifier><identifier>CODEN: ITNNEP</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Associative memory ; Computational intelligence ; Computer networks ; Design methodology ; Gray-scale ; Integrals ; Laboratories ; Landscapes ; Mathematical analysis ; Networks ; Neural networks ; Neurons ; Recurrent neural networks ; State-space methods ; Stores ; Vectors</subject><ispartof>IEEE transaction on neural networks and learning systems, 2003-07, Vol.14 (4), p.891-899</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2003</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c470t-58712f633f4c875181da6fea9d4af4593feb09700db556665468602ff15ef3e23</citedby><cites>FETCH-LOGICAL-c470t-58712f633f4c875181da6fea9d4af4593feb09700db556665468602ff15ef3e23</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1215405$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1215405$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/18238068$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Muezzinoglu, M.K.</creatorcontrib><creatorcontrib>Guzelis, C.</creatorcontrib><creatorcontrib>Zurada, J.M.</creatorcontrib><title>A new design method for the complex-valued multistate Hopfield associative memory</title><title>IEEE transaction on neural networks and learning systems</title><addtitle>TNN</addtitle><addtitle>IEEE Trans Neural Netw</addtitle><description>A method to store each element of an integral memory set M /spl sub/ {1,2,...,K}/sup n/ as a fixed point into a complex-valued multistate Hopfield network is introduced. The method employs a set of inequalities to render each memory pattern as a strict local minimum of a quadratic energy landscape. Based on the solution of this system, it gives a recurrent network of n multistate neurons with complex and symmetric synaptic weights, which operates on the finite state space {1,2,...,K}/sup n/ to minimize this quadratic functional. Maximum number of integral vectors that can be embedded into the energy landscape of the network by this method is investigated by computer experiments. This paper also enlightens the performance of the proposed method in reconstructing noisy gray-scale images.</description><subject>Associative memory</subject><subject>Computational intelligence</subject><subject>Computer networks</subject><subject>Design methodology</subject><subject>Gray-scale</subject><subject>Integrals</subject><subject>Laboratories</subject><subject>Landscapes</subject><subject>Mathematical analysis</subject><subject>Networks</subject><subject>Neural networks</subject><subject>Neurons</subject><subject>Recurrent neural networks</subject><subject>State-space methods</subject><subject>Stores</subject><subject>Vectors</subject><issn>1045-9227</issn><issn>2162-237X</issn><issn>1941-0093</issn><issn>2162-2388</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2003</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNqF0c9rFTEQB_Agiq3VswdBggc97etMfudYitpCaSnUc8jbndgtuy_PzW61_31T3oOCBz1lIJ8ZmPky9h5hhQj--ObyciUA5MqhdEq9YIfoFTYAXr6sNSjdeCHsAXtTyh0AKg3mNTtAJ6QD4w7Z9Qnf0G_eUel_bvhI823ueMoTn2-Jt3ncDvSnuY_DQh0fl2Huyxxn4md5m3oaOh5LyW0f5_6eaveYp4e37FWKQ6F3-_eI_fj29eb0rLm4-n5-enLRtMrC3GhnUSQjZVKtsxoddtEkir5TMSntZaI1eAvQrbU2xmhlnAGREmpKkoQ8Yl92c7dT_rVQmcPYl5aGIW4oLyV4QIto5f-llUoorwxU-fmfUjhljXemwk9_wbu8TJu6b_ACnPH1zhUd71A75VImSmE79WOcHgJCeIov1PjCU3xhF1_t-Lgfu6xH6p79Pq8KPuxAT0TP3wK1Ai0fAQMdnHM</recordid><startdate>20030701</startdate><enddate>20030701</enddate><creator>Muezzinoglu, M.K.</creator><creator>Guzelis, C.</creator><creator>Zurada, J.M.</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>RIA</scope><scope>RIE</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QF</scope><scope>7QO</scope><scope>7QP</scope><scope>7QQ</scope><scope>7QR</scope><scope>7SC</scope><scope>7SE</scope><scope>7SP</scope><scope>7SR</scope><scope>7TA</scope><scope>7TB</scope><scope>7TK</scope><scope>7U5</scope><scope>8BQ</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>H8D</scope><scope>JG9</scope><scope>JQ2</scope><scope>KR7</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>P64</scope><scope>7X8</scope></search><sort><creationdate>20030701</creationdate><title>A new design method for the complex-valued multistate Hopfield associative memory</title><author>Muezzinoglu, M.K. ; Guzelis, C. ; Zurada, J.M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c470t-58712f633f4c875181da6fea9d4af4593feb09700db556665468602ff15ef3e23</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2003</creationdate><topic>Associative memory</topic><topic>Computational intelligence</topic><topic>Computer networks</topic><topic>Design methodology</topic><topic>Gray-scale</topic><topic>Integrals</topic><topic>Laboratories</topic><topic>Landscapes</topic><topic>Mathematical analysis</topic><topic>Networks</topic><topic>Neural networks</topic><topic>Neurons</topic><topic>Recurrent neural networks</topic><topic>State-space methods</topic><topic>Stores</topic><topic>Vectors</topic><toplevel>online_resources</toplevel><creatorcontrib>Muezzinoglu, M.K.</creatorcontrib><creatorcontrib>Guzelis, C.</creatorcontrib><creatorcontrib>Zurada, J.M.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Aluminium Industry Abstracts</collection><collection>Biotechnology Research Abstracts</collection><collection>Calcium & Calcified Tissue Abstracts</collection><collection>Ceramic Abstracts</collection><collection>Chemoreception Abstracts</collection><collection>Computer and Information Systems Abstracts</collection><collection>Corrosion Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>Materials Business File</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Neurosciences Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Civil Engineering Abstracts</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 and BioEngineering Abstracts</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE transaction on neural networks and learning systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Muezzinoglu, M.K.</au><au>Guzelis, C.</au><au>Zurada, J.M.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A new design method for the complex-valued multistate Hopfield associative memory</atitle><jtitle>IEEE transaction on neural networks and learning systems</jtitle><stitle>TNN</stitle><addtitle>IEEE Trans Neural Netw</addtitle><date>2003-07-01</date><risdate>2003</risdate><volume>14</volume><issue>4</issue><spage>891</spage><epage>899</epage><pages>891-899</pages><issn>1045-9227</issn><issn>2162-237X</issn><eissn>1941-0093</eissn><eissn>2162-2388</eissn><coden>ITNNEP</coden><abstract>A method to store each element of an integral memory set M /spl sub/ {1,2,...,K}/sup n/ as a fixed point into a complex-valued multistate Hopfield network is introduced. The method employs a set of inequalities to render each memory pattern as a strict local minimum of a quadratic energy landscape. Based on the solution of this system, it gives a recurrent network of n multistate neurons with complex and symmetric synaptic weights, which operates on the finite state space {1,2,...,K}/sup n/ to minimize this quadratic functional. Maximum number of integral vectors that can be embedded into the energy landscape of the network by this method is investigated by computer experiments. This paper also enlightens the performance of the proposed method in reconstructing noisy gray-scale images.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>18238068</pmid><doi>10.1109/TNN.2003.813844</doi><tpages>9</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1045-9227 |
| ispartof | IEEE transaction on neural networks and learning systems, 2003-07, Vol.14 (4), p.891-899 |
| issn | 1045-9227 2162-237X 1941-0093 2162-2388 |
| language | eng |
| recordid | cdi_ieee_primary_1215405 |
| source | IEEE Electronic Library (IEL) |
| subjects | Associative memory Computational intelligence Computer networks Design methodology Gray-scale Integrals Laboratories Landscapes Mathematical analysis Networks Neural networks Neurons Recurrent neural networks State-space methods Stores Vectors |
| title | A new design method for the complex-valued multistate Hopfield associative memory |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T22%3A21%3A10IST&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=A%20new%20design%20method%20for%20the%20complex-valued%20multistate%20Hopfield%20associative%20memory&rft.jtitle=IEEE%20transaction%20on%20neural%20networks%20and%20learning%20systems&rft.au=Muezzinoglu,%20M.K.&rft.date=2003-07-01&rft.volume=14&rft.issue=4&rft.spage=891&rft.epage=899&rft.pages=891-899&rft.issn=1045-9227&rft.eissn=1941-0093&rft.coden=ITNNEP&rft_id=info:doi/10.1109/TNN.2003.813844&rft_dat=%3Cproquest_RIE%3E734249460%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=920869506&rft_id=info:pmid/18238068&rft_ieee_id=1215405&rfr_iscdi=true |