NEURO-COMPUTER
PURPOSE:To make it possible to use a neural chip having small storage capacity by providing the neuro-computer with an arithmetic means for calculating the 2nd output function value corresponding to the 2nd input value by difference between input values calculated by a quantizing means and the 1st i...
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Patent |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | FUNABASHI KENICHI |
| description | PURPOSE:To make it possible to use a neural chip having small storage capacity by providing the neuro-computer with an arithmetic means for calculating the 2nd output function value corresponding to the 2nd input value by difference between input values calculated by a quantizing means and the 1st input value stored in a storage means. CONSTITUTION:The neuro-computer 3 arranging an input device 1 and a general purpose computer 2 on the outside is provided with a memory 4 to be a storage means, a computing element 5 to be the quantizing means and a microprocessor 6 to be an arithmetic means. The storage means stores the 1st output function value corresponding to the 1st input value, the quantizing means quantizes the 2nd input value and calculates a difference between the 2nd and 1st input values and the arithmetic means receives the calculated difference between the input values from the quantizing means and the stored 1st output function value from the storage means and calculates the 2nd output function value corresponding to the 2nd input value. Consequently, a sigmoid function can be accurately calculated by using a neural chip having small storage capacity. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_JPH03168862A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>JPH03168862A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_JPH03168862A3</originalsourceid><addsrcrecordid>eNrjZODzcw0N8td19vcNCA1xDeJhYE1LzClO5YXS3AyKbq4hzh66qQX58anFBYnJqXmpJfFeAR4GxoZmFhZmRo7GxKgBAOAaHWA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>NEURO-COMPUTER</title><source>esp@cenet</source><creator>FUNABASHI KENICHI</creator><creatorcontrib>FUNABASHI KENICHI</creatorcontrib><description>PURPOSE:To make it possible to use a neural chip having small storage capacity by providing the neuro-computer with an arithmetic means for calculating the 2nd output function value corresponding to the 2nd input value by difference between input values calculated by a quantizing means and the 1st input value stored in a storage means. CONSTITUTION:The neuro-computer 3 arranging an input device 1 and a general purpose computer 2 on the outside is provided with a memory 4 to be a storage means, a computing element 5 to be the quantizing means and a microprocessor 6 to be an arithmetic means. The storage means stores the 1st output function value corresponding to the 1st input value, the quantizing means quantizes the 2nd input value and calculates a difference between the 2nd and 1st input values and the arithmetic means receives the calculated difference between the input values from the quantizing means and the stored 1st output function value from the storage means and calculates the 2nd output function value corresponding to the 2nd input value. Consequently, a sigmoid function can be accurately calculated by using a neural chip having small storage capacity.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>1991</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=19910722&DB=EPODOC&CC=JP&NR=H03168862A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=19910722&DB=EPODOC&CC=JP&NR=H03168862A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>FUNABASHI KENICHI</creatorcontrib><title>NEURO-COMPUTER</title><description>PURPOSE:To make it possible to use a neural chip having small storage capacity by providing the neuro-computer with an arithmetic means for calculating the 2nd output function value corresponding to the 2nd input value by difference between input values calculated by a quantizing means and the 1st input value stored in a storage means. CONSTITUTION:The neuro-computer 3 arranging an input device 1 and a general purpose computer 2 on the outside is provided with a memory 4 to be a storage means, a computing element 5 to be the quantizing means and a microprocessor 6 to be an arithmetic means. The storage means stores the 1st output function value corresponding to the 1st input value, the quantizing means quantizes the 2nd input value and calculates a difference between the 2nd and 1st input values and the arithmetic means receives the calculated difference between the input values from the quantizing means and the stored 1st output function value from the storage means and calculates the 2nd output function value corresponding to the 2nd input value. Consequently, a sigmoid function can be accurately calculated by using a neural chip having small storage capacity.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>1991</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZODzcw0N8td19vcNCA1xDeJhYE1LzClO5YXS3AyKbq4hzh66qQX58anFBYnJqXmpJfFeAR4GxoZmFhZmRo7GxKgBAOAaHWA</recordid><startdate>19910722</startdate><enddate>19910722</enddate><creator>FUNABASHI KENICHI</creator><scope>EVB</scope></search><sort><creationdate>19910722</creationdate><title>NEURO-COMPUTER</title><author>FUNABASHI KENICHI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_JPH03168862A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>1991</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>FUNABASHI KENICHI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>FUNABASHI KENICHI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>NEURO-COMPUTER</title><date>1991-07-22</date><risdate>1991</risdate><abstract>PURPOSE:To make it possible to use a neural chip having small storage capacity by providing the neuro-computer with an arithmetic means for calculating the 2nd output function value corresponding to the 2nd input value by difference between input values calculated by a quantizing means and the 1st input value stored in a storage means. CONSTITUTION:The neuro-computer 3 arranging an input device 1 and a general purpose computer 2 on the outside is provided with a memory 4 to be a storage means, a computing element 5 to be the quantizing means and a microprocessor 6 to be an arithmetic means. The storage means stores the 1st output function value corresponding to the 1st input value, the quantizing means quantizes the 2nd input value and calculates a difference between the 2nd and 1st input values and the arithmetic means receives the calculated difference between the input values from the quantizing means and the stored 1st output function value from the storage means and calculates the 2nd output function value corresponding to the 2nd input value. Consequently, a sigmoid function can be accurately calculated by using a neural chip having small storage capacity.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_JPH03168862A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | NEURO-COMPUTER |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-07T10%3A32%3A36IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=FUNABASHI%20KENICHI&rft.date=1991-07-22&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EJPH03168862A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |