Title:
機械学習方法、機械学習システム及び非一時的コンピュータ可読記憶媒体
Document Type and Number:
Japanese Patent JP7226696
Kind Code:
B2
Abstract:
A machine learning method includes steps of: (a) obtaining initial values of hyperparameters and hypernetwork parameters; (b) generating first classification model parameters according to the hyperparameters and the hypernetwork parameters, and updating the hypernetwork parameters according to a classification result based on the first classification model parameters relative to a training sample; (c) generating second classification model parameters according to the hyperparameters and the updated hypernetwork parameters, and updating the hyperparameters according to another classification result based on the second classification model parameters relative to a verification sample; and (d) repeating the steps (b) and (c) for updating the hypernetwork parameters and the hyperparameters.
Inventors:
Zhihung Chen
Zhang Zhehan
Zhang Jiwei
Zhang Zhehan
Zhang Jiwei
Application Number:
JP2021094808A
Publication Date:
February 21, 2023
Filing Date:
June 04, 2021
Export Citation:
Assignee:
Hongda International Electronics Co., Ltd.
International Classes:
G06N3/0985; G06N3/0475; G06T7/00; G06V10/82
Domestic Patent References:
| JP2020087103A |
Foreign References:
| US20190251439 | ||||
| WO2020070876A1 |
Attorney, Agent or Firm:
Satoshi Watanabe
Kazuko Fujita
Kazuko Fujita