Title:
SYSTEM AND METHOD FOR MODEL COMPOSITION OF NEURAL NETWORKS
Document Type and Number:
WIPO Patent Application WO/2022/261950
Kind Code:
A1
Abstract:
Method and system for generating a composite neural network (NN) model that is based on a group of source NN models, including providing a dataset including a plurality of input samples to each of the source NN models; receiving, from each of the source NN models, a respective set of label predictions for the input samples of the dataset; selecting, from among the received sets of label predictions, representative label predictions to use as pseudo-labels for the input samples; and performing supervised training of a target NN model using the pseudo-labels and the input samples to generate the composite NN model.
More Like This:
| WO/2022/149928 | SLOPE MEASUREMENT DEVICE |
| JPH04336040 | LEARNING METHOD FOR NEURAL NETWORK |
| WO/2021/253938 | NEURAL NETWORK TRAINING METHOD AND APPARATUS, AND VIDEO RECOGNITION METHOD AND APPARATUS |
Inventors:
BANITALEBI DEHKORDI AMIN (CA)
KANG XINYU (CA)
BAI XIAOLONG (CN)
ZHANG YONG (CA)
KANG XINYU (CA)
BAI XIAOLONG (CN)
ZHANG YONG (CA)
Application Number:
PCT/CN2021/100957
Publication Date:
December 22, 2022
Filing Date:
June 18, 2021
Export Citation:
Assignee:
HUAWEI CLOUD COMPUTING TECH CO LTD (CN)
International Classes:
G06N3/08
Foreign References:
| CN112633354A | 2021-04-09 | |||
| CN110289097A | 2019-09-27 | |||
| CN111199539A | 2020-05-26 | |||
| US20210150330A1 | 2021-05-20 | |||
| US20200293570A1 | 2020-09-17 | |||
| US20200065384A1 | 2020-02-27 |
Download PDF:
Previous Patent: FLEXIBLE PACKAGE FOR ARTICLES
Next Patent: DISPLAY SUBSTRATE AND MANUFACTURING METHOD THEREFOR, DISPLAY DEVICE, AND MASK
Next Patent: DISPLAY SUBSTRATE AND MANUFACTURING METHOD THEREFOR, DISPLAY DEVICE, AND MASK