PACKING MACHINE LEARNING MODELS USING PRUNING AND PERMUTATION

An example system includes a processor to prune a machine learning model based on an importance of neurons or weights. The processor is to further permute and pack remaining neurons or weights of the pruned machine learning model to reduce an amount of ciphertext computation under a selected constra...

Full description

Saved in:
Bibliographic Details
Main Authors PAL, Subhankar, BUYUKTOSUNOGLU, Alper, VACULIN, Roman, AHARONI, Ehud, SOCEANU, Omri, SARPATWAR, Kanthi, DRUCKER, Nir, SHAUL, Hayim, BARUCH, Moran, BOSE, Pradip
Format Patent
LanguageEnglish
French
Published 11.01.2024
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online AccessGet full text

Cover

Abstract An example system includes a processor to prune a machine learning model based on an importance of neurons or weights. The processor is to further permute and pack remaining neurons or weights of the pruned machine learning model to reduce an amount of ciphertext computation under a selected constraint. Un système donné à titre d'exemple comprend un processeur conçu pour élaguer un modèle d'apprentissage automatique sur la base d'une importance de neurones ou de poids. Le processeur est conçu en outre pour permuter et conditionner des neurones ou des poids restants du modèle d'apprentissage automatique élagué, afin de réduire une quantité de calcul de texte chiffré selon une contrainte sélectionnée.
AbstractList An example system includes a processor to prune a machine learning model based on an importance of neurons or weights. The processor is to further permute and pack remaining neurons or weights of the pruned machine learning model to reduce an amount of ciphertext computation under a selected constraint. Un système donné à titre d'exemple comprend un processeur conçu pour élaguer un modèle d'apprentissage automatique sur la base d'une importance de neurones ou de poids. Le processeur est conçu en outre pour permuter et conditionner des neurones ou des poids restants du modèle d'apprentissage automatique élagué, afin de réduire une quantité de calcul de texte chiffré selon une contrainte sélectionnée.
Author VACULIN, Roman
BARUCH, Moran
PAL, Subhankar
AHARONI, Ehud
SARPATWAR, Kanthi
SHAUL, Hayim
BUYUKTOSUNOGLU, Alper
DRUCKER, Nir
BOSE, Pradip
SOCEANU, Omri
Author_xml – fullname: PAL, Subhankar
– fullname: BUYUKTOSUNOGLU, Alper
– fullname: VACULIN, Roman
– fullname: AHARONI, Ehud
– fullname: SOCEANU, Omri
– fullname: SARPATWAR, Kanthi
– fullname: DRUCKER, Nir
– fullname: SHAUL, Hayim
– fullname: BARUCH, Moran
– fullname: BOSE, Pradip
BookMark eNrjYmDJy89L5WSwDXB09vb0c1fwdXT28PRzVfBxdQzyAwv4u7j6BCuEBoM4AUGhYEFHPxeFANcg39AQxxBPfz8eBta0xJziVF4ozc2g7OYa4uyhm1qQH59aXJCYnJqXWhIf7m9kYGRiYGBpaGrqaGhMnCoA6GsshA
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
DocumentTitleAlternate CONDITIONNEMENT DE MODÈLES D'APPRENTISSAGE AUTOMATIQUE VIA UN ÉLAGAGE ET UNE PERMUTATION
ExternalDocumentID WO2024009155A1
GroupedDBID EVB
ID FETCH-epo_espacenet_WO2024009155A13
IEDL.DBID EVB
IngestDate Fri Jul 19 13:02:38 EDT 2024
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
French
LinkModel DirectLink
MergedId FETCHMERGED-epo_espacenet_WO2024009155A13
Notes Application Number: WO2023IB55565
OpenAccessLink https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240111&DB=EPODOC&CC=WO&NR=2024009155A1
ParticipantIDs epo_espacenet_WO2024009155A1
PublicationCentury 2000
PublicationDate 20240111
PublicationDateYYYYMMDD 2024-01-11
PublicationDate_xml – month: 01
  year: 2024
  text: 20240111
  day: 11
PublicationDecade 2020
PublicationYear 2024
RelatedCompanies INTERNATIONAL BUSINESS MACHINES CORPORATION
IBM ISRAEL - SCIENCE & TECHNOLOGY LTD
RelatedCompanies_xml – name: INTERNATIONAL BUSINESS MACHINES CORPORATION
– name: IBM ISRAEL - SCIENCE & TECHNOLOGY LTD
Score 3.5123138
Snippet An example system includes a processor to prune a machine learning model based on an importance of neurons or weights. The processor is to further permute and...
SourceID epo
SourceType Open Access Repository
SubjectTerms CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Title PACKING MACHINE LEARNING MODELS USING PRUNING AND PERMUTATION
URI https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240111&DB=EPODOC&locale=&CC=WO&NR=2024009155A1
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dS8MwED_G_HzTqfgxpaDsrdjaduseinRptinrB3XTvY2mSUGQbriK_76XuOme9pgLHJeDy-V3uQ-AO0MwwxSWgdjEzXS7YFxnbZbpbtfusNzheactC5zDqD2c2M9TZ1qDj3UtjOoT-q2aI6JF5WjvlbqvF_9BrEDlVi7v2TuS5o_9sRe0VugY3ZO03aDn0SQOYtIiBHFbK0p_9wzZDN1HrLQjH9Ky0z597cm6lMWmU-kfwW6C_MrqGGqibMABWc9ea8B-uPrybsCeytHMl0hc2eHyBLzEJ4i7B1rok-FTRLUR9dNIEeKAjl40OU1joCXpRBH9KNASmoaTsYpIncJtn47JUEeJZn8KmL3Fm-JbZ1Av56U4B43bBuduYRocj_Ng2a7FujznmXCdIuOCX0BzG6fL7dtXcCiXMuBgmk2oV59f4hpdcMVulOZ-AJPihKU
link.rule.ids 230,309,786,891,25594,76906
linkProvider European Patent Office
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dT8JADG8IfuCbogYVdYmGt8UtbDAeiBm3wdB9ZQ7ljex2R2JiBpEZ_317JyhPvLZJ0zTptb9ePwDuNU41nbc1xCZWphpzylTaoZlq9YwuzU2WdztiwDkIO97EeJqa0wp8bGZh5J7Qb7kcET0qR38v5Xu9_C9iObK3cvVA35G0eBymfae1RscYnoTvOoO-G0dORFqEIG5rhckvTxPL0G3ESntdsZ9XJE-vAzGXstwOKsNj2I9RXlGeQIUXdaiRze21OhwG6y_vOhzIHs18hcS1H65OoR_bBHH3SAls4o1DV_FdOwklIXJc_0UR1zRGSpxMJNEOHSV2k2CSyorUGdwN3ZR4Kmo0-zPA7C3aVr99DtViUfAGKMzQGLPmusbMHuZFhtWmPZazjFvmPGOcXUBzl6TL3exbqHlp4M_8cfh8BUeCJYoPut6Eavn5xa8xHJf0RlrxB_D3h5I
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=PACKING+MACHINE+LEARNING+MODELS+USING+PRUNING+AND+PERMUTATION&rft.inventor=PAL%2C+Subhankar&rft.inventor=BUYUKTOSUNOGLU%2C+Alper&rft.inventor=VACULIN%2C+Roman&rft.inventor=AHARONI%2C+Ehud&rft.inventor=SOCEANU%2C+Omri&rft.inventor=SARPATWAR%2C+Kanthi&rft.inventor=DRUCKER%2C+Nir&rft.inventor=SHAUL%2C+Hayim&rft.inventor=BARUCH%2C+Moran&rft.inventor=BOSE%2C+Pradip&rft.date=2024-01-11&rft.externalDBID=A1&rft.externalDocID=WO2024009155A1