SOURCE-FREE ACTIVE ADAPTATION TO DISTRIBUTIONAL SHIFTS FOR MACHINE LEARNING

Disclosed is an example solution to perform source-free active adaptation to distributional shifts for machine learning. The example solution includes: interface circuitry; programmable circuitry; and instructions to cause the programmable circuitry to: perform a first training of a neural network o...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Machireddy, Amrutha, Krishnan, Ranganath, Tickoo, Omesh, Ahuja, Nilesh
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	Machireddy, Amrutha Krishnan, Ranganath Tickoo, Omesh Ahuja, Nilesh
description	Disclosed is an example solution to perform source-free active adaptation to distributional shifts for machine learning. The example solution includes: interface circuitry; programmable circuitry; and instructions to cause the programmable circuitry to: perform a first training of a neural network on a baseline data set associated with a first data distribution; compare data of a shifted data set to a threshold uncertainty value, wherein the threshold uncertainty value is associated with a distributional shift between the baseline data set and the shifted data set; generate a shifted data subset including items of the shifted dataset that satisfy the threshold uncertainty value; and perform a second training of the neural network based on the shifted data subset.
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2023137905A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2023137905A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2023137905A13</originalsourceid><addsrcrecordid>eNrjZPAO9g8NcnbVdQtydVVwdA7xDANSLo4BIY4hnv5-CiH-Ci6ewSFBnk6hIL6jj0Kwh6dbSLCCm3-Qgq-js4enn6uCj6tjkJ-nnzsPA2taYk5xKi-U5mZQdnMNcfbQTS3Ij08tLkhMTs1LLYkPDTYyMDI2NDa3NDB1NDQmThUAUdgutA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>SOURCE-FREE ACTIVE ADAPTATION TO DISTRIBUTIONAL SHIFTS FOR MACHINE LEARNING</title><source>esp@cenet</source><creator>Machireddy, Amrutha ; Krishnan, Ranganath ; Tickoo, Omesh ; Ahuja, Nilesh</creator><creatorcontrib>Machireddy, Amrutha ; Krishnan, Ranganath ; Tickoo, Omesh ; Ahuja, Nilesh</creatorcontrib><description>Disclosed is an example solution to perform source-free active adaptation to distributional shifts for machine learning. The example solution includes: interface circuitry; programmable circuitry; and instructions to cause the programmable circuitry to: perform a first training of a neural network on a baseline data set associated with a first data distribution; compare data of a shifted data set to a threshold uncertainty value, wherein the threshold uncertainty value is associated with a distributional shift between the baseline data set and the shifted data set; generate a shifted data subset including items of the shifted dataset that satisfy the threshold uncertainty value; and perform a second training of the neural network based on the shifted data subset.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; 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=20230504&DB=EPODOC&CC=US&NR=2023137905A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230504&DB=EPODOC&CC=US&NR=2023137905A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Machireddy, Amrutha</creatorcontrib><creatorcontrib>Krishnan, Ranganath</creatorcontrib><creatorcontrib>Tickoo, Omesh</creatorcontrib><creatorcontrib>Ahuja, Nilesh</creatorcontrib><title>SOURCE-FREE ACTIVE ADAPTATION TO DISTRIBUTIONAL SHIFTS FOR MACHINE LEARNING</title><description>Disclosed is an example solution to perform source-free active adaptation to distributional shifts for machine learning. The example solution includes: interface circuitry; programmable circuitry; and instructions to cause the programmable circuitry to: perform a first training of a neural network on a baseline data set associated with a first data distribution; compare data of a shifted data set to a threshold uncertainty value, wherein the threshold uncertainty value is associated with a distributional shift between the baseline data set and the shifted data set; generate a shifted data subset including items of the shifted dataset that satisfy the threshold uncertainty value; and perform a second training of the neural network based on the shifted data subset.</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZPAO9g8NcnbVdQtydVVwdA7xDANSLo4BIY4hnv5-CiH-Ci6ewSFBnk6hIL6jj0Kwh6dbSLCCm3-Qgq-js4enn6uCj6tjkJ-nnzsPA2taYk5xKi-U5mZQdnMNcfbQTS3Ij08tLkhMTs1LLYkPDTYyMDI2NDa3NDB1NDQmThUAUdgutA</recordid><startdate>20230504</startdate><enddate>20230504</enddate><creator>Machireddy, Amrutha</creator><creator>Krishnan, Ranganath</creator><creator>Tickoo, Omesh</creator><creator>Ahuja, Nilesh</creator><scope>EVB</scope></search><sort><creationdate>20230504</creationdate><title>SOURCE-FREE ACTIVE ADAPTATION TO DISTRIBUTIONAL SHIFTS FOR MACHINE LEARNING</title><author>Machireddy, Amrutha ; Krishnan, Ranganath ; Tickoo, Omesh ; Ahuja, Nilesh</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2023137905A13</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>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Machireddy, Amrutha</creatorcontrib><creatorcontrib>Krishnan, Ranganath</creatorcontrib><creatorcontrib>Tickoo, Omesh</creatorcontrib><creatorcontrib>Ahuja, Nilesh</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Machireddy, Amrutha</au><au>Krishnan, Ranganath</au><au>Tickoo, Omesh</au><au>Ahuja, Nilesh</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>SOURCE-FREE ACTIVE ADAPTATION TO DISTRIBUTIONAL SHIFTS FOR MACHINE LEARNING</title><date>2023-05-04</date><risdate>2023</risdate><abstract>Disclosed is an example solution to perform source-free active adaptation to distributional shifts for machine learning. The example solution includes: interface circuitry; programmable circuitry; and instructions to cause the programmable circuitry to: perform a first training of a neural network on a baseline data set associated with a first data distribution; compare data of a shifted data set to a threshold uncertainty value, wherein the threshold uncertainty value is associated with a distributional shift between the baseline data set and the shifted data set; generate a shifted data subset including items of the shifted dataset that satisfy the threshold uncertainty value; and perform a second training of the neural network based on the shifted data subset.</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	eng
recordid	cdi_epo_espacenet_US2023137905A1
source	esp@cenet
subjects	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS
title	SOURCE-FREE ACTIVE ADAPTATION TO DISTRIBUTIONAL SHIFTS FOR MACHINE LEARNING
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T18%3A50%3A32IST&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=Machireddy,%20Amrutha&rft.date=2023-05-04&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2023137905A1%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