Method of enhancing the performance of a neural network

A method for enhancing the performance of an artificially intelligent system employing a neural network by proving an optimized training set for training the neural network. The optimized training set is produced by identifying and removing inaccurate training pairs in the training set.

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: WASSERMAN, PHILIP D
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 WASSERMAN
PHILIP D
description A method for enhancing the performance of an artificially intelligent system employing a neural network by proving an optimized training set for training the neural network. The optimized training set is produced by identifying and removing inaccurate training pairs in the training set.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US5561741A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US5561741A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US5561741A3</originalsourceid><addsrcrecordid>eNrjZDD3TS3JyE9RyE9TSM3LSMxLzsxLVyjJSFUoSC1Kyy_KBYqkgiQTFfJSS4sSc4BUSXl-UTYPA2taYk5xKi-U5maQd3MNcfbQTS3Ij08tLkhMTgWqjA8NNjU1MzQ3MXQ0JqwCAP_BLP0</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Method of enhancing the performance of a neural network</title><source>esp@cenet</source><creator>WASSERMAN; PHILIP D</creator><creatorcontrib>WASSERMAN; PHILIP D</creatorcontrib><description>A method for enhancing the performance of an artificially intelligent system employing a neural network by proving an optimized training set for training the neural network. The optimized training set is produced by identifying and removing inaccurate training pairs in the training set.</description><edition>6</edition><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>1996</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=19961001&amp;DB=EPODOC&amp;CC=US&amp;NR=5561741A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=19961001&amp;DB=EPODOC&amp;CC=US&amp;NR=5561741A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WASSERMAN; PHILIP D</creatorcontrib><title>Method of enhancing the performance of a neural network</title><description>A method for enhancing the performance of an artificially intelligent system employing a neural network by proving an optimized training set for training the neural network. The optimized training set is produced by identifying and removing inaccurate training pairs in the training set.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>1996</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZDD3TS3JyE9RyE9TSM3LSMxLzsxLVyjJSFUoSC1Kyy_KBYqkgiQTFfJSS4sSc4BUSXl-UTYPA2taYk5xKi-U5maQd3MNcfbQTS3Ij08tLkhMTgWqjA8NNjU1MzQ3MXQ0JqwCAP_BLP0</recordid><startdate>19961001</startdate><enddate>19961001</enddate><creator>WASSERMAN; PHILIP D</creator><scope>EVB</scope></search><sort><creationdate>19961001</creationdate><title>Method of enhancing the performance of a neural network</title><author>WASSERMAN; PHILIP D</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US5561741A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>1996</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>WASSERMAN; PHILIP D</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WASSERMAN; PHILIP D</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Method of enhancing the performance of a neural network</title><date>1996-10-01</date><risdate>1996</risdate><abstract>A method for enhancing the performance of an artificially intelligent system employing a neural network by proving an optimized training set for training the neural network. The optimized training set is produced by identifying and removing inaccurate training pairs in the training set.</abstract><edition>6</edition><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US5561741A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title Method of enhancing the performance of a neural network
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T15%3A28%3A46IST&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=WASSERMAN;%20PHILIP%20D&rft.date=1996-10-01&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS5561741A%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