Connectionist Architectures for Artificial Intelligence
Features of connectionist architectures (CA) in massively parallel computers for AI applications are discussed. A CA involves a large number of simple processors, each connected to a number of the other processors. Each processor has only a small amount of memory, yet the array can cumulatively stor...
Gespeichert in:
| Veröffentlicht in: | Computer (Long Beach, Calif.) Calif.), 1987-01, Vol.20 (1), p.100-109 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 109 |
|---|---|
| container_issue | 1 |
| container_start_page | 100 |
| container_title | Computer (Long Beach, Calif.) |
| container_volume | 20 |
| creator | Fahlman, Scotte HINTON, GEOFFREYE |
| description | Features of connectionist architectures (CA) in massively parallel computers for AI applications are discussed. A CA involves a large number of simple processors, each connected to a number of the other processors. Each processor has only a small amount of memory, yet the array can cumulatively store a large amount of data which can be altered by changing the connections among the processors. Each processor is also limited to a few simple arithmetic or Boolean operations. A sufficient number of processors must be available for processing the subtasks of any task assigned the machine. Approaches for performing pattern recognition and learning tasks with CAs are explored. Consideration is given to the NETL system, which uses local representations and marker-passing techniques, a value-passing system, back-propagation, constraint-satisfication in iterative networks, and the Boltzmann learning scheme. (M.S.K.) |
| doi_str_mv | 10.1109/MC.1987.1663364 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_1663364</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1663364</ieee_id><sourcerecordid>24394686</sourcerecordid><originalsourceid>FETCH-LOGICAL-c379t-266ca35fe79352ada82fefcb3d649edf37971bf56a3fa851a9769279d48c7d453</originalsourceid><addsrcrecordid>eNqNkTlPAzEQhS0EEiFQU9BEFHSb-D7KaMURKREN1JbjtYnRZh1sp-Dfs6uNRAnV6M18M3qaB8AtgnOEoFps6jlSUswR54RwegYmiDFZQYnoOZhAiGSlEMeX4Crnz15SycgEiDp2nbMlxC7kMlsmuwul18fk8szH1HdK8MEG085WXXFtGz5cZ901uPCmze7mVKfg_enxrX6p1q_Pq3q5riwRqlSYc2sI804owrBpjMTeebslDafKNb6HBNp6xg3xRjJklOAKC9VQaUVDGZmC-_FuzCXobAdzOzt61gIpCPkAPYzQIcWvo8tF70O2vVfTuXjMGksh-5eov0FKFOWS_wvEGA4XFyNoU8w5Oa8PKexN-tYI6iEXvan1kIs-5dJv3I0bwTn3S5-mP3PFh_Y</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>24392209</pqid></control><display><type>article</type><title>Connectionist Architectures for Artificial Intelligence</title><source>IEEE/IET Electronic Library</source><creator>Fahlman, Scotte ; HINTON, GEOFFREYE</creator><creatorcontrib>Fahlman, Scotte ; HINTON, GEOFFREYE ; Carnegie-Mellon Univ</creatorcontrib><description>Features of connectionist architectures (CA) in massively parallel computers for AI applications are discussed. A CA involves a large number of simple processors, each connected to a number of the other processors. Each processor has only a small amount of memory, yet the array can cumulatively store a large amount of data which can be altered by changing the connections among the processors. Each processor is also limited to a few simple arithmetic or Boolean operations. A sufficient number of processors must be available for processing the subtasks of any task assigned the machine. Approaches for performing pattern recognition and learning tasks with CAs are explored. Consideration is given to the NETL system, which uses local representations and marker-passing techniques, a value-passing system, back-propagation, constraint-satisfication in iterative networks, and the Boltzmann learning scheme. (M.S.K.)</description><identifier>ISSN: 0018-9162</identifier><identifier>EISSN: 1558-0814</identifier><identifier>DOI: 10.1109/MC.1987.1663364</identifier><identifier>CODEN: CPTRB4</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>990210 - Supercomputers- (1987-1989) ; Acoustic noise ; ARTIFICIAL INTELLIGENCE ; COMPUTER ARCHITECTURE ; COMPUTERS ; DIGITAL COMPUTERS ; GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE ; Intelligent networks ; Intelligent sensors ; KNOWLEDGE BASE ; Machine intelligence ; Medical diagnosis ; MEMORY DEVICES ; Parallel architectures ; PARALLEL PROCESSING ; PROGRAMMING ; RESEARCH PROGRAMS ; Shape ; Speech recognition ; SUPERCOMPUTERS</subject><ispartof>Computer (Long Beach, Calif.), 1987-01, Vol.20 (1), p.100-109</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c379t-266ca35fe79352ada82fefcb3d649edf37971bf56a3fa851a9769279d48c7d453</citedby><cites>FETCH-LOGICAL-c379t-266ca35fe79352ada82fefcb3d649edf37971bf56a3fa851a9769279d48c7d453</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1663364$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,885,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1663364$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.osti.gov/biblio/7190065$$D View this record in Osti.gov$$Hfree_for_read</backlink></links><search><creatorcontrib>Fahlman, Scotte</creatorcontrib><creatorcontrib>HINTON, GEOFFREYE</creatorcontrib><creatorcontrib>Carnegie-Mellon Univ</creatorcontrib><title>Connectionist Architectures for Artificial Intelligence</title><title>Computer (Long Beach, Calif.)</title><addtitle>MC</addtitle><description>Features of connectionist architectures (CA) in massively parallel computers for AI applications are discussed. A CA involves a large number of simple processors, each connected to a number of the other processors. Each processor has only a small amount of memory, yet the array can cumulatively store a large amount of data which can be altered by changing the connections among the processors. Each processor is also limited to a few simple arithmetic or Boolean operations. A sufficient number of processors must be available for processing the subtasks of any task assigned the machine. Approaches for performing pattern recognition and learning tasks with CAs are explored. Consideration is given to the NETL system, which uses local representations and marker-passing techniques, a value-passing system, back-propagation, constraint-satisfication in iterative networks, and the Boltzmann learning scheme. (M.S.K.)</description><subject>990210 - Supercomputers- (1987-1989)</subject><subject>Acoustic noise</subject><subject>ARTIFICIAL INTELLIGENCE</subject><subject>COMPUTER ARCHITECTURE</subject><subject>COMPUTERS</subject><subject>DIGITAL COMPUTERS</subject><subject>GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE</subject><subject>Intelligent networks</subject><subject>Intelligent sensors</subject><subject>KNOWLEDGE BASE</subject><subject>Machine intelligence</subject><subject>Medical diagnosis</subject><subject>MEMORY DEVICES</subject><subject>Parallel architectures</subject><subject>PARALLEL PROCESSING</subject><subject>PROGRAMMING</subject><subject>RESEARCH PROGRAMS</subject><subject>Shape</subject><subject>Speech recognition</subject><subject>SUPERCOMPUTERS</subject><issn>0018-9162</issn><issn>1558-0814</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1987</creationdate><recordtype>article</recordtype><recordid>eNqNkTlPAzEQhS0EEiFQU9BEFHSb-D7KaMURKREN1JbjtYnRZh1sp-Dfs6uNRAnV6M18M3qaB8AtgnOEoFps6jlSUswR54RwegYmiDFZQYnoOZhAiGSlEMeX4Crnz15SycgEiDp2nbMlxC7kMlsmuwul18fk8szH1HdK8MEG085WXXFtGz5cZ901uPCmze7mVKfg_enxrX6p1q_Pq3q5riwRqlSYc2sI804owrBpjMTeebslDafKNb6HBNp6xg3xRjJklOAKC9VQaUVDGZmC-_FuzCXobAdzOzt61gIpCPkAPYzQIcWvo8tF70O2vVfTuXjMGksh-5eov0FKFOWS_wvEGA4XFyNoU8w5Oa8PKexN-tYI6iEXvan1kIs-5dJv3I0bwTn3S5-mP3PFh_Y</recordid><startdate>198701</startdate><enddate>198701</enddate><creator>Fahlman, Scotte</creator><creator>HINTON, GEOFFREYE</creator><general>IEEE</general><scope>AAYXX</scope><scope>CITATION</scope><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope><scope>7SC</scope><scope>JQ2</scope><scope>L~C</scope><scope>L~D</scope><scope>7SP</scope><scope>OTOTI</scope></search><sort><creationdate>198701</creationdate><title>Connectionist Architectures for Artificial Intelligence</title><author>Fahlman, Scotte ; HINTON, GEOFFREYE</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c379t-266ca35fe79352ada82fefcb3d649edf37971bf56a3fa851a9769279d48c7d453</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1987</creationdate><topic>990210 - Supercomputers- (1987-1989)</topic><topic>Acoustic noise</topic><topic>ARTIFICIAL INTELLIGENCE</topic><topic>COMPUTER ARCHITECTURE</topic><topic>COMPUTERS</topic><topic>DIGITAL COMPUTERS</topic><topic>GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE</topic><topic>Intelligent networks</topic><topic>Intelligent sensors</topic><topic>KNOWLEDGE BASE</topic><topic>Machine intelligence</topic><topic>Medical diagnosis</topic><topic>MEMORY DEVICES</topic><topic>Parallel architectures</topic><topic>PARALLEL PROCESSING</topic><topic>PROGRAMMING</topic><topic>RESEARCH PROGRAMS</topic><topic>Shape</topic><topic>Speech recognition</topic><topic>SUPERCOMPUTERS</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Fahlman, Scotte</creatorcontrib><creatorcontrib>HINTON, GEOFFREYE</creatorcontrib><creatorcontrib>Carnegie-Mellon Univ</creatorcontrib><collection>CrossRef</collection><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts</collection><collection>ProQuest Computer Science Collection</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Electronics & Communications Abstracts</collection><collection>OSTI.GOV</collection><jtitle>Computer (Long Beach, Calif.)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Fahlman, Scotte</au><au>HINTON, GEOFFREYE</au><aucorp>Carnegie-Mellon Univ</aucorp><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Connectionist Architectures for Artificial Intelligence</atitle><jtitle>Computer (Long Beach, Calif.)</jtitle><stitle>MC</stitle><date>1987-01</date><risdate>1987</risdate><volume>20</volume><issue>1</issue><spage>100</spage><epage>109</epage><pages>100-109</pages><issn>0018-9162</issn><eissn>1558-0814</eissn><coden>CPTRB4</coden><abstract>Features of connectionist architectures (CA) in massively parallel computers for AI applications are discussed. A CA involves a large number of simple processors, each connected to a number of the other processors. Each processor has only a small amount of memory, yet the array can cumulatively store a large amount of data which can be altered by changing the connections among the processors. Each processor is also limited to a few simple arithmetic or Boolean operations. A sufficient number of processors must be available for processing the subtasks of any task assigned the machine. Approaches for performing pattern recognition and learning tasks with CAs are explored. Consideration is given to the NETL system, which uses local representations and marker-passing techniques, a value-passing system, back-propagation, constraint-satisfication in iterative networks, and the Boltzmann learning scheme. (M.S.K.)</abstract><cop>United States</cop><pub>IEEE</pub><doi>10.1109/MC.1987.1663364</doi><tpages>10</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 0018-9162 |
| ispartof | Computer (Long Beach, Calif.), 1987-01, Vol.20 (1), p.100-109 |
| issn | 0018-9162 1558-0814 |
| language | eng |
| recordid | cdi_ieee_primary_1663364 |
| source | IEEE/IET Electronic Library |
| subjects | 990210 - Supercomputers- (1987-1989) Acoustic noise ARTIFICIAL INTELLIGENCE COMPUTER ARCHITECTURE COMPUTERS DIGITAL COMPUTERS GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE Intelligent networks Intelligent sensors KNOWLEDGE BASE Machine intelligence Medical diagnosis MEMORY DEVICES Parallel architectures PARALLEL PROCESSING PROGRAMMING RESEARCH PROGRAMS Shape Speech recognition SUPERCOMPUTERS |
| title | Connectionist Architectures for Artificial Intelligence |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T09%3A11%3A59IST&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=Connectionist%20Architectures%20for%20Artificial%20Intelligence&rft.jtitle=Computer%20(Long%20Beach,%20Calif.)&rft.au=Fahlman,%20Scotte&rft.aucorp=Carnegie-Mellon%20Univ&rft.date=1987-01&rft.volume=20&rft.issue=1&rft.spage=100&rft.epage=109&rft.pages=100-109&rft.issn=0018-9162&rft.eissn=1558-0814&rft.coden=CPTRB4&rft_id=info:doi/10.1109/MC.1987.1663364&rft_dat=%3Cproquest_RIE%3E24394686%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=24392209&rft_id=info:pmid/&rft_ieee_id=1663364&rfr_iscdi=true |