Computer-Implemented Method for Training Multi-Task Neural Network
Summary
EPO published patent application EP4437455A1 for a computer-implemented method for training multi-task neural networks. The patent names Sorbonne Université, CNRS, and Datakalab as applicants. The invention relates to G06N 3/04, G06N 20/20, and G06N 3/08 classifications and is designated across 31 European states including DE, FR, GB, IT, ES, NL, and others.
What changed
EPO published patent EP4437455A1 for a computer-implemented method of training multi-task neural networks. The invention, classified under G06N, involves shared representations with task-specific heads and auxiliary loss mechanisms. Applicants include Sorbonne Université, CNRS, and Datakalab.
Patent holders gain exclusive rights to the claimed technology in designated European states. Technology companies developing multi-task AI systems may need to assess potential licensing requirements or infringement risks.
Archived snapshot
Apr 18, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
COMPUTER-IMPLEMENTED METHOD FOR TRAINING A MULTI-TASK NETWORK
Publication EP4437455A1 Kind: A1 Apr 08, 2026
Applicants
SORBONNE UNIVERSITE, Centre National de la Recherche Scientifique, Datakalab
Inventors
BAILLY, Kevin, TALLEC, Gauthier, DAPOGNY, Arnaud
IPC Classifications
G06N 3/04 20230101AFI20230602BHEP G06N 20/20 20190101ALI20230602BHEP G06N 3/08 20230101ALI20230602BHEP
Designated States
AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LI, LT, LU, LV, MC, ME, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR
Related changes
Get daily alerts for EPO Patent Bulletin - AI & Computing (G06N)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from EPO.
The summary, classification, recommended actions, deadlines, and penalty information are AI-generated from the original text and may contain errors. Always verify against the source document.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when EPO Patent Bulletin - AI & Computing (G06N) publishes new changes.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.