Neural network training method and device, electronic equipment and storage medium

The invention provides a neural network training method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining training data and a plurality of target neural networks obtained through training; performing feature extraction on the training data by using...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: HE YINAN, WANG KUN, HUANG GENGSHI, TENG JIANING, CHEN SIYU, SHAO JING
Format: Patent
Sprache:chi ; 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 HE YINAN
WANG KUN
HUANG GENGSHI
TENG JIANING
CHEN SIYU
SHAO JING
description The invention provides a neural network training method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining training data and a plurality of target neural networks obtained through training; performing feature extraction on the training data by using a plurality of target neural networks to obtain feature information output by a feature extraction layer included in each target neural network; based on the feature information output by the feature extraction layer included in each target neural network, determining a loss function value of a joint neural network to be trained, wherein the joint neural network is composed of a plurality of target neural networks and a connection layer between the feature extraction layers included in each target neural network; and carrying out at least one round of network training on the to-be-trained joint neural network based on the loss function value to obtain a trained joint neural network. According to the invention, the
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN114004357A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN114004357A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN114004357A3</originalsourceid><addsrcrecordid>eNqNjb0KwjAURrM4iPoO112hpRVnKYpTB3EvIfmsweQm5kdf3yI-gNNZzuHMxaVHidISI799fFCO0rDhkRzy3WuSrEnjZRQ2BAuVo2ejCM9iggPnr5Cyj3LE1GhT3FLMbtImrH5ciPXpeO3OWwQ_IAWpMN2Grq_rtqraZrc_NP84HzCGODE</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Neural network training method and device, electronic equipment and storage medium</title><source>esp@cenet</source><creator>HE YINAN ; WANG KUN ; HUANG GENGSHI ; TENG JIANING ; CHEN SIYU ; SHAO JING</creator><creatorcontrib>HE YINAN ; WANG KUN ; HUANG GENGSHI ; TENG JIANING ; CHEN SIYU ; SHAO JING</creatorcontrib><description>The invention provides a neural network training method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining training data and a plurality of target neural networks obtained through training; performing feature extraction on the training data by using a plurality of target neural networks to obtain feature information output by a feature extraction layer included in each target neural network; based on the feature information output by the feature extraction layer included in each target neural network, determining a loss function value of a joint neural network to be trained, wherein the joint neural network is composed of a plurality of target neural networks and a connection layer between the feature extraction layers included in each target neural network; and carrying out at least one round of network training on the to-be-trained joint neural network based on the loss function value to obtain a trained joint neural network. According to the invention, the</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; HANDLING RECORD CARRIERS ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2022</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=20220201&amp;DB=EPODOC&amp;CC=CN&amp;NR=114004357A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20220201&amp;DB=EPODOC&amp;CC=CN&amp;NR=114004357A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>HE YINAN</creatorcontrib><creatorcontrib>WANG KUN</creatorcontrib><creatorcontrib>HUANG GENGSHI</creatorcontrib><creatorcontrib>TENG JIANING</creatorcontrib><creatorcontrib>CHEN SIYU</creatorcontrib><creatorcontrib>SHAO JING</creatorcontrib><title>Neural network training method and device, electronic equipment and storage medium</title><description>The invention provides a neural network training method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining training data and a plurality of target neural networks obtained through training; performing feature extraction on the training data by using a plurality of target neural networks to obtain feature information output by a feature extraction layer included in each target neural network; based on the feature information output by the feature extraction layer included in each target neural network, determining a loss function value of a joint neural network to be trained, wherein the joint neural network is composed of a plurality of target neural networks and a connection layer between the feature extraction layers included in each target neural network; and carrying out at least one round of network training on the to-be-trained joint neural network based on the loss function value to obtain a trained joint neural network. According to the invention, the</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>HANDLING RECORD CARRIERS</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjb0KwjAURrM4iPoO112hpRVnKYpTB3EvIfmsweQm5kdf3yI-gNNZzuHMxaVHidISI799fFCO0rDhkRzy3WuSrEnjZRQ2BAuVo2ejCM9iggPnr5Cyj3LE1GhT3FLMbtImrH5ciPXpeO3OWwQ_IAWpMN2Grq_rtqraZrc_NP84HzCGODE</recordid><startdate>20220201</startdate><enddate>20220201</enddate><creator>HE YINAN</creator><creator>WANG KUN</creator><creator>HUANG GENGSHI</creator><creator>TENG JIANING</creator><creator>CHEN SIYU</creator><creator>SHAO JING</creator><scope>EVB</scope></search><sort><creationdate>20220201</creationdate><title>Neural network training method and device, electronic equipment and storage medium</title><author>HE YINAN ; WANG KUN ; HUANG GENGSHI ; TENG JIANING ; CHEN SIYU ; SHAO JING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN114004357A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>HANDLING RECORD CARRIERS</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>HE YINAN</creatorcontrib><creatorcontrib>WANG KUN</creatorcontrib><creatorcontrib>HUANG GENGSHI</creatorcontrib><creatorcontrib>TENG JIANING</creatorcontrib><creatorcontrib>CHEN SIYU</creatorcontrib><creatorcontrib>SHAO JING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>HE YINAN</au><au>WANG KUN</au><au>HUANG GENGSHI</au><au>TENG JIANING</au><au>CHEN SIYU</au><au>SHAO JING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Neural network training method and device, electronic equipment and storage medium</title><date>2022-02-01</date><risdate>2022</risdate><abstract>The invention provides a neural network training method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining training data and a plurality of target neural networks obtained through training; performing feature extraction on the training data by using a plurality of target neural networks to obtain feature information output by a feature extraction layer included in each target neural network; based on the feature information output by the feature extraction layer included in each target neural network, determining a loss function value of a joint neural network to be trained, wherein the joint neural network is composed of a plurality of target neural networks and a connection layer between the feature extraction layers included in each target neural network; and carrying out at least one round of network training on the to-be-trained joint neural network based on the loss function value to obtain a trained joint neural network. According to the invention, the</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN114004357A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
HANDLING RECORD CARRIERS
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
title Neural network training method and device, electronic equipment and storage medium
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T18%3A36%3A49IST&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=HE%20YINAN&rft.date=2022-02-01&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN114004357A%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