WO2023071285 - GENERATIVE ADVERSARIAL NEURAL ARCHITECTURE SEARCH
National phase entry is expected:
Publication Number
WO/2023/071285
Publication Date
04.05.2023
International Application No.
PCT/CN2022/104321
International Filing Date
07.07.2022
Title **
[English]
GENERATIVE ADVERSARIAL NEURAL ARCHITECTURE SEARCH
[French]
RECHERCHE D'ARCHITECTURE NEURONALE ANTAGONISTE GÉNÉRATIVE
Applicants **
HUAWEI TECHNOLOGIES CO., LTD.
Huawei Administration Building, Bantian,Longgang District
Shenzhen, Guangdong 518129, CN
Inventors
CHANGIZ REZAEI, Seyed Saeed
1205-1668 Davie Street
Vancouver, British Columbia V6G 0C4, CA
HAN, Fred Xuefei
8466 Sloane Cres. NW
Edmonton, Alberta T6R 0L2, CA
NIU, Di
1203 Hainstock Green SW
Edmonton, Alberta T6W 3B6, CA
Priority Data
17/516,025
01.11.2021
US
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 | 1425 | |
| EPO | Filing, Examination | 9225 | |
| Japan | Filing | 589 | |
| South Korea | Filing | 575 | |
| USA | Filing, Examination | 2710 |
Total: 14524 USD
The term for entry into the National Phase has expired. This quotation is for informational purposes only
Abstract[English]
A method and system for neural architectural search (NAS) for performing a task. A generative adversarial network comprising a generator and a discriminator receives, from a user device, a query for neural network architecture, the query including a search space. The generator of the generative adversarial network generates a plurality of generated neural network architectures responsive to the received search space. The discriminator of the generative adversarial network selects an optimal neural network architecture from among the plurality of generated neural network architectures. The optimal generated neural network architecture is transmitted to the user device.[French]
L'invention concerne un procédé et un système de recherche d'architecturale neuronale (RAN) en vue d'effectuer une tâche. Un réseau antagoniste génératif comprenant un générateur et un discriminateur reçoit, en provenance d'un dispositif d'utilisateur, une interrogation pour une architecture de réseau neuronal, l'interrogation comprenant un espace de recherche. Le générateur du réseau antagoniste génératif génère une pluralité d'architectures de réseau neuronal générées en réponse à l'espace de recherche reçu. Le discriminateur du réseau antagoniste génératif sélectionne une architecture de réseau neuronal optimale parmi la pluralité d'architectures de réseau neuronal générées. L'architecture de réseau neuronal générée optimale est transmise au dispositif d'utilisateur.