WO2023070655 - INTERFACING WITH CODED INFERENCE NETWORKS
National phase entry:
Publication Number
WO/2023/070655
Publication Date
04.05.2023
International Application No.
PCT/CN2021/127892
International Filing Date
01.11.2021
Title **
[English]
INTERFACING WITH CODED INFERENCE NETWORKS
[French]
INTERFAÇAGE AVEC DES RÉSEAUX D'INFÉRENCES CODÉS
Applicants **
HUAWEI TECHNOLOGIES CO., LTD.
Huawei Administration Building, Bantian, Longgang District
Shenzhen, Guangdong 518129, CN
Inventors
GE, Yiqun
Huawei Administration Building, Bantian, Longgang District
Shenzhen, Guangdong 518129, CN
SHI, Wuxian
Huawei Administration Building, Bantian, Longgang District
Shenzhen, Guangdong 518129, CN
TONG, Wen
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 | 1699 | |
| EPO | Filing, Examination | 10095 | |
| Japan | Filing | 587 | |
| South Korea | Filing | 482 | |
| USA | Filing, Examination | 3310 |
Total: 16173 USD
The term for entry into the National Phase has expired. This quotation is for informational purposes only
Abstract[English]
Some embodiments of the present disclosure relate to inferencing using a trained deep neural network. Inferencing may, reasonably, be expected to be a mainstream application of 6G wireless networks. Agile, robust and accurate inferencing is important for the success of AI applications. Aspects of the present application relate to introducing coding theory into inferencing in a distributed manner. It may be shown that redundant wireless bandwidths and edge units help to ensure agility, robustness and accuracy in coded inferencing networks.[French]
Certains modes de réalisation de la présente divulgation se rapportent à l'inférence à l'aide d'un réseau neuronal profond formé. On peut, de manière raisonnable, s'attendre à ce que l'inférence soit une application courante de réseaux sans fil 6G. Une inférence souple, robuste et précise est importante pour la réussite des applications IA. Des aspects de la présente demande se rapportent à l'introduction d'une théorie de codage dans l'inférence d'une manière distribuée. On peut montrer que des bandes passantes sans fil et des unités périphériques redondantes aident à garantir la souplesse, la robustesse et la précision dans des réseaux d'inférences codés.