Method of processing information in artificial neural networks

Method of processing information in artificial neural networks

A method of processing information in an artificial neural network comprising a plurality of artificial neurons (1a to 1n) and weighted links (2) coupling the neurons. In the method, those of the artificial neurons (1a to 1n) whose output values change by a value greater than a threshold value (T) a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: SUZUOKA, TAKASHI
Format: Patent
Sprache:eng ; fre ; ger
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
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 SUZUOKA, TAKASHI
description A method of processing information in an artificial neural network comprising a plurality of artificial neurons (1a to 1n) and weighted links (2) coupling the neurons. In the method, those of the artificial neurons (1a to 1n) whose output values change by a value greater than a threshold value (T) are selected. The output values of the selected neurons are calculated, and the influence which the changes in the output values of the selected neurons impose on the input values of the other artificial neurons is computed. The threshold value (T) is changed such that an appropriate number of neurons are selected. The information processing in the artificial neural network is stopped when the threshold value decreased below a predetermined small value and the values output by all artificial neurons change by a value equal to or less than the threshold value.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP0410805A2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP0410805A2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP0410805A23</originalsourceid><addsrcrecordid>eNrjZLDzTS3JyE9RyE9TKCjKT04tLs7MS1fIzEvLL8pNLMnMzwOyFRKLSjLTMpMzE3MU8lJLi8BUSXl-UXYxDwNrWmJOcSovlOZmUHBzDXH20E0tyI9PLS5ITE4FKo13DTAwMTSwMDB1NDImQgkAL4Ywnw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Method of processing information in artificial neural networks</title><source>esp@cenet</source><creator>SUZUOKA, TAKASHI</creator><creatorcontrib>SUZUOKA, TAKASHI</creatorcontrib><description>A method of processing information in an artificial neural network comprising a plurality of artificial neurons (1a to 1n) and weighted links (2) coupling the neurons. In the method, those of the artificial neurons (1a to 1n) whose output values change by a value greater than a threshold value (T) are selected. The output values of the selected neurons are calculated, and the influence which the changes in the output values of the selected neurons impose on the input values of the other artificial neurons is computed. The threshold value (T) is changed such that an appropriate number of neurons are selected. The information processing in the artificial neural network is stopped when the threshold value decreased below a predetermined small value and the values output by all artificial neurons change by a value equal to or less than the threshold value.</description><language>eng ; fre ; ger</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&amp;date=19910130&amp;DB=EPODOC&amp;CC=EP&amp;NR=0410805A2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=19910130&amp;DB=EPODOC&amp;CC=EP&amp;NR=0410805A2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SUZUOKA, TAKASHI</creatorcontrib><title>Method of processing information in artificial neural networks</title><description>A method of processing information in an artificial neural network comprising a plurality of artificial neurons (1a to 1n) and weighted links (2) coupling the neurons. In the method, those of the artificial neurons (1a to 1n) whose output values change by a value greater than a threshold value (T) are selected. The output values of the selected neurons are calculated, and the influence which the changes in the output values of the selected neurons impose on the input values of the other artificial neurons is computed. The threshold value (T) is changed such that an appropriate number of neurons are selected. The information processing in the artificial neural network is stopped when the threshold value decreased below a predetermined small value and the values output by all artificial neurons change by a value equal to or less than the threshold value.</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>eNrjZLDzTS3JyE9RyE9TKCjKT04tLs7MS1fIzEvLL8pNLMnMzwOyFRKLSjLTMpMzE3MU8lJLi8BUSXl-UXYxDwNrWmJOcSovlOZmUHBzDXH20E0tyI9PLS5ITE4FKo13DTAwMTSwMDB1NDImQgkAL4Ywnw</recordid><startdate>19910130</startdate><enddate>19910130</enddate><creator>SUZUOKA, TAKASHI</creator><scope>EVB</scope></search><sort><creationdate>19910130</creationdate><title>Method of processing information in artificial neural networks</title><author>SUZUOKA, TAKASHI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP0410805A23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</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>SUZUOKA, TAKASHI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SUZUOKA, TAKASHI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Method of processing information in artificial neural networks</title><date>1991-01-30</date><risdate>1991</risdate><abstract>A method of processing information in an artificial neural network comprising a plurality of artificial neurons (1a to 1n) and weighted links (2) coupling the neurons. In the method, those of the artificial neurons (1a to 1n) whose output values change by a value greater than a threshold value (T) are selected. The output values of the selected neurons are calculated, and the influence which the changes in the output values of the selected neurons impose on the input values of the other artificial neurons is computed. The threshold value (T) is changed such that an appropriate number of neurons are selected. The information processing in the artificial neural network is stopped when the threshold value decreased below a predetermined small value and the values output by all artificial neurons change by a value equal to or less than the threshold value.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; fre ; ger
recordid cdi_epo_espacenet_EP0410805A2
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title Method of processing information in artificial neural networks
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-18T15%3A50%3A55IST&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=SUZUOKA,%20TAKASHI&rft.date=1991-01-30&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP0410805A2%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