Management of graphical symbols in a CAD environment: A neural network approach
A new neural network called AUGURS is designed to assist a user of a computer-aided design package in utilizing standard graphical symbols. AUGURS is similar to the Zipcode Net by Le Cun et al. (1989, 1990) in its encoding of transformation knowledge into its network structure, but is much more comp...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 279 |
|---|---|
| container_issue | |
| container_start_page | 272 |
| container_title | |
| container_volume | |
| creator | Yang, D.S. Webster, J.L. Renmdell, L.A. Garrett, J.H. Shaw, D.S. |
| description | A new neural network called AUGURS is designed to assist a user of a computer-aided design package in utilizing standard graphical symbols. AUGURS is similar to the Zipcode Net by Le Cun et al. (1989, 1990) in its encoding of transformation knowledge into its network structure, but is much more compact and efficient. The experiments compare AUGURS with two versions of the Zipcode Net and a traditional layered feedforward network with an unconstrained structure. The experimental results show that AUGURS can recognize a user-drawn symbol with better accuracy and plausibility than the other networks with the least amount of recognition time when the number of training examples is limited. |
| doi_str_mv | 10.1109/TAI.1993.633967 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>proquest_6IE</sourceid><recordid>TN_cdi_ieee_primary_633967</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>633967</ieee_id><sourcerecordid>26088702</sourcerecordid><originalsourceid>FETCH-LOGICAL-i203t-8d7c8ef742c38b316c4ad26ee5c3de8c5d76299b18445c0f277bfa5196d6a92c3</originalsourceid><addsrcrecordid>eNot0DtPwzAUBWBLgERbmJGYPLEl-JH4wRaVV6WiLmWOHOemNSROsFNQ_z1BZbrLd86RLkI3lKSUEn2_LVYp1ZqngnMt5BmaE0WVyBgh-hzNKBE8EZKTSzSP8YOQPKc8m6HNm_FmBx34EfcN3gUz7J01LY7HrurbiJ3HBi-LRwz-24Xe_8kHXGAPhzAxD-NPHz6xGYbQG7u_QheNaSNc_98Fen9-2i5fk_XmZbUs1oljhI-JqqVV0MiMWa4qToXNTM0EQG55DcrmtRRM64qqLMstaZiUVWNyqkUtjJ5CC3R36p1mvw4Qx7Jz0ULbGg_9IZZMEKUkYRO8PUEHAOUQXGfCsTw9if8C7QhawA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype><pqid>26088702</pqid></control><display><type>conference_proceeding</type><title>Management of graphical symbols in a CAD environment: A neural network approach</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Yang, D.S. ; Webster, J.L. ; Renmdell, L.A. ; Garrett, J.H. ; Shaw, D.S.</creator><creatorcontrib>Yang, D.S. ; Webster, J.L. ; Renmdell, L.A. ; Garrett, J.H. ; Shaw, D.S.</creatorcontrib><description>A new neural network called AUGURS is designed to assist a user of a computer-aided design package in utilizing standard graphical symbols. AUGURS is similar to the Zipcode Net by Le Cun et al. (1989, 1990) in its encoding of transformation knowledge into its network structure, but is much more compact and efficient. The experiments compare AUGURS with two versions of the Zipcode Net and a traditional layered feedforward network with an unconstrained structure. The experimental results show that AUGURS can recognize a user-drawn symbol with better accuracy and plausibility than the other networks with the least amount of recognition time when the number of training examples is limited.</description><identifier>ISSN: 1063-6730</identifier><identifier>ISBN: 0818642009</identifier><identifier>ISBN: 9780818642005</identifier><identifier>DOI: 10.1109/TAI.1993.633967</identifier><language>eng</language><publisher>IEEE</publisher><subject>Application software ; Buildings ; Computer network management ; Design automation ; Environmental management ; Floppy disks ; Intelligent networks ; Libraries ; Neural networks ; Standardization</subject><ispartof>Proceedings of 1993 IEEE Conference on Tools with Al (TAI-93), 1993, p.272-279</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/633967$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,314,780,784,789,790,2058,4050,4051,27924,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/633967$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Yang, D.S.</creatorcontrib><creatorcontrib>Webster, J.L.</creatorcontrib><creatorcontrib>Renmdell, L.A.</creatorcontrib><creatorcontrib>Garrett, J.H.</creatorcontrib><creatorcontrib>Shaw, D.S.</creatorcontrib><title>Management of graphical symbols in a CAD environment: A neural network approach</title><title>Proceedings of 1993 IEEE Conference on Tools with Al (TAI-93)</title><addtitle>TAI</addtitle><description>A new neural network called AUGURS is designed to assist a user of a computer-aided design package in utilizing standard graphical symbols. AUGURS is similar to the Zipcode Net by Le Cun et al. (1989, 1990) in its encoding of transformation knowledge into its network structure, but is much more compact and efficient. The experiments compare AUGURS with two versions of the Zipcode Net and a traditional layered feedforward network with an unconstrained structure. The experimental results show that AUGURS can recognize a user-drawn symbol with better accuracy and plausibility than the other networks with the least amount of recognition time when the number of training examples is limited.</description><subject>Application software</subject><subject>Buildings</subject><subject>Computer network management</subject><subject>Design automation</subject><subject>Environmental management</subject><subject>Floppy disks</subject><subject>Intelligent networks</subject><subject>Libraries</subject><subject>Neural networks</subject><subject>Standardization</subject><issn>1063-6730</issn><isbn>0818642009</isbn><isbn>9780818642005</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>1993</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNot0DtPwzAUBWBLgERbmJGYPLEl-JH4wRaVV6WiLmWOHOemNSROsFNQ_z1BZbrLd86RLkI3lKSUEn2_LVYp1ZqngnMt5BmaE0WVyBgh-hzNKBE8EZKTSzSP8YOQPKc8m6HNm_FmBx34EfcN3gUz7J01LY7HrurbiJ3HBi-LRwz-24Xe_8kHXGAPhzAxD-NPHz6xGYbQG7u_QheNaSNc_98Fen9-2i5fk_XmZbUs1oljhI-JqqVV0MiMWa4qToXNTM0EQG55DcrmtRRM64qqLMstaZiUVWNyqkUtjJ5CC3R36p1mvw4Qx7Jz0ULbGg_9IZZMEKUkYRO8PUEHAOUQXGfCsTw9if8C7QhawA</recordid><startdate>1993</startdate><enddate>1993</enddate><creator>Yang, D.S.</creator><creator>Webster, J.L.</creator><creator>Renmdell, L.A.</creator><creator>Garrett, J.H.</creator><creator>Shaw, D.S.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</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>1993</creationdate><title>Management of graphical symbols in a CAD environment: A neural network approach</title><author>Yang, D.S. ; Webster, J.L. ; Renmdell, L.A. ; Garrett, J.H. ; Shaw, D.S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i203t-8d7c8ef742c38b316c4ad26ee5c3de8c5d76299b18445c0f277bfa5196d6a92c3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>1993</creationdate><topic>Application software</topic><topic>Buildings</topic><topic>Computer network management</topic><topic>Design automation</topic><topic>Environmental management</topic><topic>Floppy disks</topic><topic>Intelligent networks</topic><topic>Libraries</topic><topic>Neural networks</topic><topic>Standardization</topic><toplevel>online_resources</toplevel><creatorcontrib>Yang, D.S.</creatorcontrib><creatorcontrib>Webster, J.L.</creatorcontrib><creatorcontrib>Renmdell, L.A.</creatorcontrib><creatorcontrib>Garrett, J.H.</creatorcontrib><creatorcontrib>Shaw, D.S.</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><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></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Yang, D.S.</au><au>Webster, J.L.</au><au>Renmdell, L.A.</au><au>Garrett, J.H.</au><au>Shaw, D.S.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Management of graphical symbols in a CAD environment: A neural network approach</atitle><btitle>Proceedings of 1993 IEEE Conference on Tools with Al (TAI-93)</btitle><stitle>TAI</stitle><date>1993</date><risdate>1993</risdate><spage>272</spage><epage>279</epage><pages>272-279</pages><issn>1063-6730</issn><isbn>0818642009</isbn><isbn>9780818642005</isbn><abstract>A new neural network called AUGURS is designed to assist a user of a computer-aided design package in utilizing standard graphical symbols. AUGURS is similar to the Zipcode Net by Le Cun et al. (1989, 1990) in its encoding of transformation knowledge into its network structure, but is much more compact and efficient. The experiments compare AUGURS with two versions of the Zipcode Net and a traditional layered feedforward network with an unconstrained structure. The experimental results show that AUGURS can recognize a user-drawn symbol with better accuracy and plausibility than the other networks with the least amount of recognition time when the number of training examples is limited.</abstract><pub>IEEE</pub><doi>10.1109/TAI.1993.633967</doi><tpages>8</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1063-6730 |
| ispartof | Proceedings of 1993 IEEE Conference on Tools with Al (TAI-93), 1993, p.272-279 |
| issn | 1063-6730 |
| language | eng |
| recordid | cdi_ieee_primary_633967 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Application software Buildings Computer network management Design automation Environmental management Floppy disks Intelligent networks Libraries Neural networks Standardization |
| title | Management of graphical symbols in a CAD environment: A neural network approach |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T15%3A23%3A50IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Management%20of%20graphical%20symbols%20in%20a%20CAD%20environment:%20A%20neural%20network%20approach&rft.btitle=Proceedings%20of%201993%20IEEE%20Conference%20on%20Tools%20with%20Al%20(TAI-93)&rft.au=Yang,%20D.S.&rft.date=1993&rft.spage=272&rft.epage=279&rft.pages=272-279&rft.issn=1063-6730&rft.isbn=0818642009&rft.isbn_list=9780818642005&rft_id=info:doi/10.1109/TAI.1993.633967&rft_dat=%3Cproquest_6IE%3E26088702%3C/proquest_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=26088702&rft_id=info:pmid/&rft_ieee_id=633967&rfr_iscdi=true |