TRAINING TRANSFER-FOCUSED MODELS FOR DEEP LEARNING

Whether to train a new neural network model can be determined based on similarity estimates between a sample data set and a plurality of source data sets associated with a plurality of prior-trained neural network models. A cluster among the plurality of prior-trained neural network models can be de...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Watson, Patrick, Bhattacharjee, Bishwaranjan, Kender, John Ronald, Huo, Siyu, Glass, Michael Robert, Codella, Noel Christopher, Dube, Parijat, Belgodere, Brian Michael, Hill, Matthew Leon
Format:	Patent
Sprache:	eng
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING 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	Watson, Patrick Bhattacharjee, Bishwaranjan Kender, John Ronald Huo, Siyu Glass, Michael Robert Codella, Noel Christopher Dube, Parijat Belgodere, Brian Michael Hill, Matthew Leon
description	Whether to train a new neural network model can be determined based on similarity estimates between a sample data set and a plurality of source data sets associated with a plurality of prior-trained neural network models. A cluster among the plurality of prior-trained neural network models can be determined. A set of training data based on the cluster can be determined. The new neural network model can be trained based on the set of training data.
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2020320379A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2020320379A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2020320379A13</originalsourceid><addsrcrecordid>eNrjZDAKCXL09PP0c1cAMvyC3VyDdN38nUODXV0UfP1dXH2CFdz8gxRcXF0DFHxcHYNAKnkYWNMSc4pTeaE0N4Oym2uIs4duakF-fGpxQWJyal5qSXxosJGBkYExEJlbOhoaE6cKABWwJ7U</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>TRAINING TRANSFER-FOCUSED MODELS FOR DEEP LEARNING</title><source>esp@cenet</source><creator>Watson, Patrick ; Bhattacharjee, Bishwaranjan ; Kender, John Ronald ; Huo, Siyu ; Glass, Michael Robert ; Codella, Noel Christopher ; Dube, Parijat ; Belgodere, Brian Michael ; Hill, Matthew Leon</creator><creatorcontrib>Watson, Patrick ; Bhattacharjee, Bishwaranjan ; Kender, John Ronald ; Huo, Siyu ; Glass, Michael Robert ; Codella, Noel Christopher ; Dube, Parijat ; Belgodere, Brian Michael ; Hill, Matthew Leon</creatorcontrib><description>Whether to train a new neural network model can be determined based on similarity estimates between a sample data set and a plurality of source data sets associated with a plurality of prior-trained neural network models. A cluster among the plurality of prior-trained neural network models can be determined. A set of training data based on the cluster can be determined. The new neural network model can be trained based on the set of training data.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2020</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=20201008&DB=EPODOC&CC=US&NR=2020320379A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20201008&DB=EPODOC&CC=US&NR=2020320379A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Watson, Patrick</creatorcontrib><creatorcontrib>Bhattacharjee, Bishwaranjan</creatorcontrib><creatorcontrib>Kender, John Ronald</creatorcontrib><creatorcontrib>Huo, Siyu</creatorcontrib><creatorcontrib>Glass, Michael Robert</creatorcontrib><creatorcontrib>Codella, Noel Christopher</creatorcontrib><creatorcontrib>Dube, Parijat</creatorcontrib><creatorcontrib>Belgodere, Brian Michael</creatorcontrib><creatorcontrib>Hill, Matthew Leon</creatorcontrib><title>TRAINING TRANSFER-FOCUSED MODELS FOR DEEP LEARNING</title><description>Whether to train a new neural network model can be determined based on similarity estimates between a sample data set and a plurality of source data sets associated with a plurality of prior-trained neural network models. A cluster among the plurality of prior-trained neural network models can be determined. A set of training data based on the cluster can be determined. The new neural network model can be trained based on the set of training data.</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>2020</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZDAKCXL09PP0c1cAMvyC3VyDdN38nUODXV0UfP1dXH2CFdz8gxRcXF0DFHxcHYNAKnkYWNMSc4pTeaE0N4Oym2uIs4duakF-fGpxQWJyal5qSXxosJGBkYExEJlbOhoaE6cKABWwJ7U</recordid><startdate>20201008</startdate><enddate>20201008</enddate><creator>Watson, Patrick</creator><creator>Bhattacharjee, Bishwaranjan</creator><creator>Kender, John Ronald</creator><creator>Huo, Siyu</creator><creator>Glass, Michael Robert</creator><creator>Codella, Noel Christopher</creator><creator>Dube, Parijat</creator><creator>Belgodere, Brian Michael</creator><creator>Hill, Matthew Leon</creator><scope>EVB</scope></search><sort><creationdate>20201008</creationdate><title>TRAINING TRANSFER-FOCUSED MODELS FOR DEEP LEARNING</title><author>Watson, Patrick ; Bhattacharjee, Bishwaranjan ; Kender, John Ronald ; Huo, Siyu ; Glass, Michael Robert ; Codella, Noel Christopher ; Dube, Parijat ; Belgodere, Brian Michael ; Hill, Matthew Leon</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2020320379A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2020</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>Watson, Patrick</creatorcontrib><creatorcontrib>Bhattacharjee, Bishwaranjan</creatorcontrib><creatorcontrib>Kender, John Ronald</creatorcontrib><creatorcontrib>Huo, Siyu</creatorcontrib><creatorcontrib>Glass, Michael Robert</creatorcontrib><creatorcontrib>Codella, Noel Christopher</creatorcontrib><creatorcontrib>Dube, Parijat</creatorcontrib><creatorcontrib>Belgodere, Brian Michael</creatorcontrib><creatorcontrib>Hill, Matthew Leon</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Watson, Patrick</au><au>Bhattacharjee, Bishwaranjan</au><au>Kender, John Ronald</au><au>Huo, Siyu</au><au>Glass, Michael Robert</au><au>Codella, Noel Christopher</au><au>Dube, Parijat</au><au>Belgodere, Brian Michael</au><au>Hill, Matthew Leon</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>TRAINING TRANSFER-FOCUSED MODELS FOR DEEP LEARNING</title><date>2020-10-08</date><risdate>2020</risdate><abstract>Whether to train a new neural network model can be determined based on similarity estimates between a sample data set and a plurality of source data sets associated with a plurality of prior-trained neural network models. A cluster among the plurality of prior-trained neural network models can be determined. A set of training data based on the cluster can be determined. The new neural network model can be trained based on the set of training data.</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	eng
recordid	cdi_epo_espacenet_US2020320379A1
source	esp@cenet
subjects	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS
title	TRAINING TRANSFER-FOCUSED MODELS FOR DEEP LEARNING
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-13T04%3A51%3A16IST&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=Watson,%20Patrick&rft.date=2020-10-08&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2020320379A1%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