Initialization of classification layers in neural networks

Example methods disclosed herein to initialize classification vectors of a neural network include ranking a plurality of classes to be represented by the classification vectors based on respective numbers of instances of training data associated with corresponding ones of the classes. Disclosed exam...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Tovar Velasco, Javier, de la Calle, Alejandro, Almazán, Emilio
Format:	Patent
Sprache:	eng
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	Tovar Velasco, Javier de la Calle, Alejandro Almazán, Emilio
description	Example methods disclosed herein to initialize classification vectors of a neural network include ranking a plurality of classes to be represented by the classification vectors based on respective numbers of instances of training data associated with corresponding ones of the classes. Disclosed example methods also include initializing the classification vectors to span a classification space corresponding to the classes. Disclosed example methods further include assigning respective ones of the classes to corresponding ones of the classification vectors based on the ranking of the classes.
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US11676034B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US11676034B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US11676034B23</originalsourceid><addsrcrecordid>eNrjZLDyzMssyUzMyaxKLMnMz1PIT1NIzkksLs5My0yGiOQkVqYWFStk5inkpZYWJeYAqZLy_KLsYh4G1rTEnOJUXijNzaDo5hri7KGbWpAfn1pckJicClQaHxpsaGhmbmZgbOJkZEyMGgDMBi_h</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Initialization of classification layers in neural networks</title><source>esp@cenet</source><creator>Tovar Velasco, Javier ; de la Calle, Alejandro ; Almazán, Emilio</creator><creatorcontrib>Tovar Velasco, Javier ; de la Calle, Alejandro ; Almazán, Emilio</creatorcontrib><description>Example methods disclosed herein to initialize classification vectors of a neural network include ranking a plurality of classes to be represented by the classification vectors based on respective numbers of instances of training data associated with corresponding ones of the classes. Disclosed example methods also include initializing the classification vectors to span a classification space corresponding to the classes. Disclosed example methods further include assigning respective ones of the classes to corresponding ones of the classification vectors based on the ranking of the classes.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2023</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=20230613&DB=EPODOC&CC=US&NR=11676034B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230613&DB=EPODOC&CC=US&NR=11676034B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Tovar Velasco, Javier</creatorcontrib><creatorcontrib>de la Calle, Alejandro</creatorcontrib><creatorcontrib>Almazán, Emilio</creatorcontrib><title>Initialization of classification layers in neural networks</title><description>Example methods disclosed herein to initialize classification vectors of a neural network include ranking a plurality of classes to be represented by the classification vectors based on respective numbers of instances of training data associated with corresponding ones of the classes. Disclosed example methods also include initializing the classification vectors to span a classification space corresponding to the classes. Disclosed example methods further include assigning respective ones of the classes to corresponding ones of the classification vectors based on the ranking of the classes.</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLDyzMssyUzMyaxKLMnMz1PIT1NIzkksLs5My0yGiOQkVqYWFStk5inkpZYWJeYAqZLy_KLsYh4G1rTEnOJUXijNzaDo5hri7KGbWpAfn1pckJicClQaHxpsaGhmbmZgbOJkZEyMGgDMBi_h</recordid><startdate>20230613</startdate><enddate>20230613</enddate><creator>Tovar Velasco, Javier</creator><creator>de la Calle, Alejandro</creator><creator>Almazán, Emilio</creator><scope>EVB</scope></search><sort><creationdate>20230613</creationdate><title>Initialization of classification layers in neural networks</title><author>Tovar Velasco, Javier ; de la Calle, Alejandro ; Almazán, Emilio</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US11676034B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2023</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>Tovar Velasco, Javier</creatorcontrib><creatorcontrib>de la Calle, Alejandro</creatorcontrib><creatorcontrib>Almazán, Emilio</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Tovar Velasco, Javier</au><au>de la Calle, Alejandro</au><au>Almazán, Emilio</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Initialization of classification layers in neural networks</title><date>2023-06-13</date><risdate>2023</risdate><abstract>Example methods disclosed herein to initialize classification vectors of a neural network include ranking a plurality of classes to be represented by the classification vectors based on respective numbers of instances of training data associated with corresponding ones of the classes. Disclosed example methods also include initializing the classification vectors to span a classification space corresponding to the classes. Disclosed example methods further include assigning respective ones of the classes to corresponding ones of the classification vectors based on the ranking of the classes.</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	eng
recordid	cdi_epo_espacenet_US11676034B2
source	esp@cenet
subjects	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS
title	Initialization of classification layers in neural networks
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-03T21%3A09%3A09IST&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=Tovar%20Velasco,%20Javier&rft.date=2023-06-13&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS11676034B2%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