Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
COMPUTER-IMPLEMENTED METHOD AND APPARATUS FOR DEEP LEARNING
Document Type and Number:
WIPO Patent Application WO/2024/031524
Kind Code:
A1
Abstract:
A computer-implemented method for deep learning comprising obtaining a meta network consisting of a set of incubating modules, wherein each of the set of incubating modules comprises at least one basic unit of an architecture of a deep learning network, and the meta network is pre-trained on a dataset; independently training, on the dataset, a set of modules with each of the set of modules corresponding to a respective one of the set of incubating modules, by training the meta network with one of the set of incubating modules being substituted by one of the set of modules corresponding to the one of the set of incubating modules on the dataset for training of the one of the set of modules, wherein module of the set of modules comprises more than one basic units of the architecture of the deep learning network; assembling the independently trained modules of the set of modules to form an assembled model; and obtaining, based at least in part on the assembled model, the deep learning network that is optimized on the dataset.

More Like This:
WO/2020/171915SYSTEM AND METHOD FOR TRANSFERRING ELECTRO-OPTICAL (EO) KNOWLEDGE FOR SYNTHETIC-APERTURE-RADAR (SAR)-BASED OBJECT DETECTION
WO/2022/237065CLASSIFICATION MODEL TRAINING METHOD, VIDEO CLASSIFICATION METHOD, AND RELATED DEVICE
WO/2024/073251MACHINE LEARNING SYSTEMS AND RELATED ASPECTS FOR GENERATING DISEASE MAPS OF POPULATIONS
Inventors:
HUANG GAO (CN)
NI ZANLIN (CN)
YU JIANGWEI (CN)
JIANG HAOJUN (CN)
WANG YULIN (CN)
SONG SHIJI (CN)
ZHANG KAIXUAN (CN)
Application Number:
PCT/CN2022/111726
Publication Date:
February 15, 2024
Filing Date:
August 11, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
BOSCH GMBH ROBERT (DE)
UNIV TSINGHUA (CN)
International Classes:
G06N3/08; G06N3/04
Domestic Patent References:
WO2021061401A12021-04-01
Foreign References:
CN108053120A2018-05-18
US20150324690A12015-11-12
CN111523639A2020-08-11
Other References:
DING YAO-XIANG, PAN SINNO JIALIN, SUGIYAMA MASASHI: "Boosting-Based Reliable Model Reuse", PROCEEDINGS OF MACHINE LEARNING RESEARCH, 1 January 2020 (2020-01-01), pages 145 - 160, XP093138963
WU XI-ZHU; XU WENKAI; LIU SONG; ZHOU ZHI-HUA: "Model Reuse With Reduced Kernel Mean Embedding Specification", IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, IEEE SERVICE CENTRE , LOS ALAMITOS , CA, US, vol. 35, no. 1, 3 June 2021 (2021-06-03), US , pages 699 - 710, XP011930013, ISSN: 1041-4347, DOI: 10.1109/TKDE.2021.3086619
Attorney, Agent or Firm:
NTD PATENT & TRADEMARK AGENCY LTD. (CN)
Download PDF:
View/Download PDF      PDF Help



 
Previous Patent: INFORMATION PROCESSING METHOD AND APPARATUS, COMMUNICATION DEVICE, AND STORAGE MEDIUM

Next Patent: METHOD AND APPARATUS FOR BI-LEVEL PHYSICS-INFORMED NEURAL NETWORKS FOR PDE CONSTRAINED OPTIMIZATION