blank Quick help
blank Maintenance news

Scheduled maintenance

Regular maintenance outages:
between 05.00 and 05.15 hrs CET (Monday to Sunday).

Other outages
Availability

2022.02.11

More...
blank News flashes

News Flashes

New version of the European Patent Register – SPC proceedings information in the Unitary Patent Register.

2024-07-24

More...
blank Related links

Release notes
European Patent Register Assistant
European Patent Register Resource Book
European Patent Register – pocket guide
FAQ - European Patent Register
Federated Register (Flyer)
Global Dossier (Flyer)
Register events
Deep link coverage
Federated Register content
The Patent Information Tour
Fair use charter

Extract from the Register of European Patents

EP About this file: EP3938898

EP3938898 - SYSTEM AND METHOD FOR IMPLEMENTING MODULAR UNIVERSAL REPARAMETERIZATION FOR DEEP MULTI-TASK LEARNING ACROSS DIVERSE DOMAINS [Right-click to bookmark this link]
StatusExamination is in progress
Status updated on  17.05.2024
Database last updated on 19.10.2024
FormerRequest for examination was made
Status updated on  17.12.2021
FormerThe international publication has been made
Status updated on  19.09.2020
Most recent event   Tooltip24.09.2024New entry: Reply to examination report 
Applicant(s)For all designated states
Cognizant Technology Solutions U.S. Corporation
211 Quality Circle
College Station, TX 77845 / US
[2022/03]
Inventor(s)01 / MEYERSON, Elliot
550 Battery, 1905
San Francisco, CA 9411 / US
02 / MIIKKULAINEN, Risto
339 Olmsted Road
Stanford, CA 94305 / US
[N/P]
Former [2022/03]01 / MEYERSON, Elliot
San Francisco, CA 9411 / US
02 / MIIKKULAINEN, Risto
Stanford, CA 94305 / US
Representative(s)Barker Brettell LLP
100 Hagley Road
Edgbaston
Birmingham, West Midlands B16 8QQ / GB
[2022/03]
Application number, filing date20770337.212.03.2020
[2022/03]
WO2020US22396
Priority number, dateUS201962817637P13.03.2019         Original published format: US 201962817637 P
[2022/03]
Filing languageEN
Procedural languageEN
PublicationType: A1 Application with search report
No.:WO2020186061
Date:17.09.2020
Language:EN
[2020/38]
Type: A1 Application with search report 
No.:EP3938898
Date:19.01.2022
Language:EN
The application published by WIPO in one of the EPO official languages on 17.09.2020 takes the place of the publication of the European patent application.
[2022/03]
Search report(s)International search report - published on:US17.09.2020
(Supplementary) European search report - dispatched on:EP24.02.2023
ClassificationIPC:G06N3/096, G06F9/455, G06F15/16, G06N99/00, G06N3/045, G06N3/084, // G06N3/086
[2023/13]
CPC:
G06N3/045 (EP,US); G06N3/047 (EP,US); G06N3/084 (EP,US);
G06N3/096 (EP); G06N3/0442 (EP); G06N3/0464 (EP);
G06N3/086 (EP) (-)
Former IPC [2022/03]G06F9/455, G06F15/16, G06N99/00
Designated contracting statesAL,   AT,   BE,   BG,   CH,   CY,   CZ,   DE,   DK,   EE,   ES,   FI,   FR,   GB,   GR,   HR,   HU,   IE,   IS,   IT,   LI,   LT,   LU,   LV,   MC,   MK,   MT,   NL,   NO,   PL,   PT,   RO,   RS,   SE,   SI,   SK,   SM,   TR [2022/03]
TitleGerman:SYSTEM UND VERFAHREN ZUR IMPLEMENTIERUNG MODULARER UNIVERSELLER REPARAMETRISIERUNG FÜR MULTI-TASK-TIEFENLERNEN ÜBER DIVERSE DOMÄNEN HINWEG[2022/03]
English:SYSTEM AND METHOD FOR IMPLEMENTING MODULAR UNIVERSAL REPARAMETERIZATION FOR DEEP MULTI-TASK LEARNING ACROSS DIVERSE DOMAINS[2022/03]
French:SYSTÈME ET PROCÉDÉ PERMETTANT DE METTRE EN OEUVRE UN REPARAMÉTRAGE UNIVERSEL MODULAIRE POUR UN APPRENTISSAGE MULTITÂCHE PROFOND À TRAVERS DIVERS DOMAINES[2022/19]
Former [2022/03]SYSTÈME ET PROCÉDÉ PERMETTANT DE METTRE EN ?UVRE UN REPARAMÉTRAGE UNIVERSEL MODULAIRE POUR UN APPRENTISSAGE MULTITÂCHE PROFOND À TRAVERS DIVERS DOMAINES
Entry into regional phase09.09.2021National basic fee paid 
09.09.2021Search fee paid 
09.09.2021Designation fee(s) paid 
09.09.2021Examination fee paid 
Examination procedure09.09.2021Examination requested  [2022/03]
25.09.2023Amendment by applicant (claims and/or description)
22.05.2024Despatch of a communication from the examining division (Time limit: M04)
23.09.2024Reply to a communication from the examining division
Fees paidRenewal fee
29.03.2022Renewal fee patent year 03
23.03.2023Renewal fee patent year 04
13.03.2024Renewal fee patent year 05
Opt-out from the exclusive  Tooltip
competence of the Unified
Patent Court		 See the Register of the Unified Patent Court for opt-out data
Responsibility for the accuracy, completeness or quality of the data displayed under the link provided lies entirely with the Unified Patent Court.
Documents cited:Search[XI]  - YOUSEFI NILOOFAR ET AL, Multi-Task Learning with Group-Specific Feature Space Sharing, 16TH EUROPEAN CONFERENCE - COMPUTER VISION - ECCV 2020, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, PAGE(S) 120 - 136, (20150829), XP047560739 [X] 1,3,4 * section 1; page 120 - page 123 * * abstract * [I] 2,5,6

DOI:   http://dx.doi.org/10.1007/978-3-319-23525-7_8
International search[Y]US2014019388  (KINGSBURY BRIAN E D [US], et al) [Y] 5, 13, 18 * entire document *;
 [A]US8775341  (COMMONS MICHAEL LAMPORT [US]) [A] 1-18 * entire document *;
 [Y]US2016232445  (SRINIVASAN PRAVEEN DEEPAK [GB], et al) [Y] 4, 11, 17, 18 * entire document *;
 [A]US2016242690  (PRINCIPE JOSE C [US], et al) [A] 1-18 * entire document *;
 [A]US2016328253  (MAJUMDAR ARUN [US]) [A] 1-18 * entire document *;
 [A]US2017063908  (MUDDU SUDHAKAR [US], et al) [A] 1-18* entire document *;
 [XY]  - MEYERSON et al., "Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing -and Back", Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden , PMLR 80, 2018 arXiv:1803.04062v2, pages 1 - 10, URL: https://arxiv.org/pdf/1803.04062.pdf, (20200510), XP080863553 [X] 1-3, 6-10, 12, 14-16 [Y] 4, 5, 11, 13, 17, 18
The EPO accepts no responsibility for the accuracy of data originating from other authorities; in particular, it does not guarantee that it is complete, up to date or fit for specific purposes.