SYSTEMS AND METHODS FOR KNOWLEDGE TRANSFER IN MACHINE LEARNING

A training system may create and train a machine learning model with knowledge transfer. The knowledge transfer may transfer knowledge that is acquired by another machine learning model that has been previously trained to the machine learning model that is under training. The knowledge transfer may...

Full description

Saved in:
Bibliographic Details
Main Authors Tao, Yunzhe, Sun, Tao, Genc, Sahika, Mallya Kasaragod, Sunil
Format Patent
LanguageEnglish
Published 10.08.2023
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

Abstract A training system may create and train a machine learning model with knowledge transfer. The knowledge transfer may transfer knowledge that is acquired by another machine learning model that has been previously trained to the machine learning model that is under training. The knowledge transfer may include a combination of representation transfer and instance transfer, the two of which may be performed alternatingly. The instance transfer may further include a filter mechanism to selectively identify instances with a satisfactory performance to implement the knowledge transfer.
AbstractList A training system may create and train a machine learning model with knowledge transfer. The knowledge transfer may transfer knowledge that is acquired by another machine learning model that has been previously trained to the machine learning model that is under training. The knowledge transfer may include a combination of representation transfer and instance transfer, the two of which may be performed alternatingly. The instance transfer may further include a filter mechanism to selectively identify instances with a satisfactory performance to implement the knowledge transfer.
Author Tao, Yunzhe
Genc, Sahika
Sun, Tao
Mallya Kasaragod, Sunil
Author_xml – fullname: Tao, Yunzhe
– fullname: Sun, Tao
– fullname: Genc, Sahika
– fullname: Mallya Kasaragod, Sunil
BookMark eNrjYmDJy89L5WSwC44MDnH1DVZw9HNR8HUN8fB3CVZw8w9S8PbzD_dxdXF3VQgJcvQLdnMNUvD0U_B1dPbw9HNV8HF1DPLz9HPnYWBNS8wpTuWF0twMym6uIc4euqkF-fGpxQWJyal5qSXxocFGBkbGRqZGxqamjobGxKkCABXrLLg
ContentType Patent
DBID EVB
DatabaseName esp@cenet
DatabaseTitleList
Database_xml – sequence: 1
  dbid: EVB
  name: esp@cenet
  url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Chemistry
Sciences
Physics
ExternalDocumentID US2023252355A1
GroupedDBID EVB
ID FETCH-epo_espacenet_US2023252355A13
IEDL.DBID EVB
IngestDate Fri Jul 19 12:46:06 EDT 2024
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-epo_espacenet_US2023252355A13
Notes Application Number: US202318193023
OpenAccessLink https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230810&DB=EPODOC&CC=US&NR=2023252355A1
ParticipantIDs epo_espacenet_US2023252355A1
PublicationCentury 2000
PublicationDate 20230810
PublicationDateYYYYMMDD 2023-08-10
PublicationDate_xml – month: 08
  year: 2023
  text: 20230810
  day: 10
PublicationDecade 2020
PublicationYear 2023
RelatedCompanies Amazon Technologies, Inc
RelatedCompanies_xml – name: Amazon Technologies, Inc
Score 3.4802184
Snippet A training system may create and train a machine learning model with knowledge transfer. The knowledge transfer may transfer knowledge that is acquired by...
SourceID epo
SourceType Open Access Repository
SubjectTerms CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Title SYSTEMS AND METHODS FOR KNOWLEDGE TRANSFER IN MACHINE LEARNING
URI https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230810&DB=EPODOC&locale=&CC=US&NR=2023252355A1
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dT8IwEL8Q_HxT1PiBpolmb4swqGMP04ytc6jryDoUnwhlIzExg8iM_763BpQnHnuXXC6XXu9-7d0V4MaQzSzFraJLU1K9PZUN3ZJjBCuUGtOONFMrKxucQ34XDNpPQzqswOeqF0bNCf1RwxHRoybo74U6r-f_l1ieqq1c3MoPJM0e_MT2tCU6xny602xoXtdm_ciLXM117YHQeKx4BoIuSh3ESluYSJulP7DXbtmXMl8PKv4BbPdRXl4cQiXLa7Dnrv5eq8FuuHzyrsGOqtGcLJC49MPFEdyLd5GwUBCHeyRkSRB5giCeI888elNTjkkSO1z4LCY9TkLHDXqckRfmxLzHH4_h2meJG-io0ujPAqOBWNe_dQLVfJZnp0DKqhY0LQZiSdupkUpptMypRa0SqI1TeQb1TZLON7MvYL9c6moCbB2qxdd3dokxuJBXynS_dx2Dvw
link.rule.ids 230,309,783,888,25576,76876
linkProvider European Patent Office
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dT8IwEL8Q_MA3RY0fqE00e1uEQR17QDO2zk1YR7ah-EQoG4mJGURm_Pe9NaA88XqXNJdLr3e_9u5XgDtNNNIEt4oqdEHV1kzUVUNMEKxQqs3aQk-MtBhw9vmDO2y9jOioBJ_rWRjJE_ojyRExoqYY77k8rxf_l1i27K1c3osPFM2fnLhjKyt0jPV0u1FX7G6HDQI7sBTL6gwjhYdSpyHootRErLSDRbZexAN77RZzKYvNpOIcwu4A18vyIyilWRUq1vrvtSrs-6sn7yrsyR7N6RKFqzhcHsNj9B7FzI-IyW3is9gN7IggniM9HrxJlmMShyaPHBYSjxPftFyPM9JnZsg9_nwCtw6LLVdFk8Z_HhgPo037m6dQzuZZegak6GpB12IiFrSVaIkQWlOfGdQogNokEedQ27bSxXb1DVTc2O-P-x7vXcJBoVIlG2wNyvnXd3qF-TgX19KNv9EMhrI
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=SYSTEMS+AND+METHODS+FOR+KNOWLEDGE+TRANSFER+IN+MACHINE+LEARNING&rft.inventor=Tao%2C+Yunzhe&rft.inventor=Sun%2C+Tao&rft.inventor=Genc%2C+Sahika&rft.inventor=Mallya+Kasaragod%2C+Sunil&rft.date=2023-08-10&rft.externalDBID=A1&rft.externalDocID=US2023252355A1