WO2023173296 - APPARATUS AND METHODS FOR MACHINE LEARNING WITH LOW TRAINING DELAY AND COMMUNICATION OVERHEAD
National phase entry:
Publication Number
WO/2023/173296
Publication Date
21.09.2023
International Application No.
PCT/CN2022/081004
International Filing Date
15.03.2022
Title **
[English]
APPARATUS AND METHODS FOR MACHINE LEARNING WITH LOW TRAINING DELAY AND COMMUNICATION OVERHEAD
[French]
APPAREIL ET PROCÉDÉS D'APPRENTISSAGE AUTOMATIQUE AVEC FAIBLE RETARD DE FORMATION ET SURCHARGE DE COMMUNICATION
Applicants **
HUAWEI TECHNOLOGIES CO.,LTD.
Huawei Administration Building, Bantian, Longgang District
Shenzhen, Guangdong 518129, CN
Inventors
TANG, Hao
Huawei Administration Building, Bantian, Longgang District
Shenzhen, Guangdong 518129, CN
ZHANG, Liqing
Suite 400, 303 Terry Fox Drive, Kanata
Ottawa, Ontario 231, CA
MA, Jianglei
Suite 400, 303 Terry Fox Drive, Kanata
Ottawa, Ontario 231, CA
Application details
| Total Number of Claims/PCT | * |
| Number of Independent Claims | * |
| Number of Priorities | * |
| Number of Multi-Dependent Claims | * |
| Number of Drawings | * |
| Pages for Publication | * |
| Number of Pages with Drawings | * |
| Pages of Specification | * |
| * | |
| * | |
International Searching Authority |
CNIPA
* |
| Applicant's Legal Status |
Legal Entity
* |
| * | |
| * | |
| * | |
| * | |
| Entry into National Phase under |
Chapter I
* |
| Translation |
|
Recalculate
* The data is based on automatic recognition. Please verify and amend if necessary.
** IP-Coster compiles data from publicly available sources. If this data includes your personal information, you can contact us to request its removal.
Quotation for National Phase entry
| Country | Stages | Total | |
|---|---|---|---|
| China | Filing | 4513 | |
| EPO | Filing, Examination | 79987 | |
| Japan | Filing | 593 | |
| South Korea | Filing | 482 | |
| USA | Filing, Examination | 25760 |
Total: 111335 USD
The term for entry into the National Phase has expired. This quotation is for informational purposes only
Abstract[English]
Current online training procedures for artificial intelligence/machine learning (AI/ML) models for wireless communication generally suffer from high communication overhead and/or significant delays in training, particularly when one or more devices participating in the training procedure has limited learning capabilities, such as limited processing capabilities, limited access to training data and/or limited sensing capabilities to collect training data. In some embodiments, a device is selectively included or excluded from participating in an online training procedure based on the device's currently reported learning capabilities in order to provide a tradeoff between overhead reductions and training performance.[French]
Des procédures de formation en ligne actuelles pour des modèles d'intelligence artificielle/d'apprentissage automatique (IA/ML) pour une communication sans fil souffrent généralement d'une surcharge de communication élevée et/ou de retards significatifs dans la formation, en particulier lorsqu'un ou plusieurs dispositifs participant à la procédure de formation présentent des capacités d'apprentissage limitées, telles que des capacités de traitement limitées, un accès limité à des données de formation et/ou des capacités de détection limitées pour collecter des données de formation. Dans certains modes de réalisation, un dispositif est sélectivement inclus ou exclu de participer à une procédure de formation en ligne sur la base des capacités d'apprentissage actuellement rapportées du dispositif afin de fournir un compromis entre des réductions de surcharge et des performances de formation.