Title:
METHOD AND SYSTEM FOR TRAINING MODEL, AND DEVICE AND MEDIUM
Document Type and Number:
WIPO Patent Application WO/2022/057465
Kind Code:
A1
Abstract:
Disclosed is a method for training a model, the method comprising the following steps: acquiring a variety of hyper-parameters to be adjusted; dividing the variety of hyper-parameters into several hyper-parameter groups according to preset priorities; sequentially sampling the several hyper-parameter groups according to a priority order and performing training verification; determining, according to the training verification result, a final hyper-parameter value corresponding to each hyper-parameter in each hyper-parameter group; and building and training a model by using the final hyper-parameter value corresponding to each hyper-parameter in each hyper-parameter group. Also disclosed are a system, a computer device, and a readable storage medium. According to the solution proposed by the present invention, when hyper-parameter sampling is performed, hyper-parameters are classified according to preset priorities, and an automatic hyper-parameter tuning algorithm is used in sequence to perform adjustment, so as to find a better hyper-parameter combination using fewer computing resources, thereby improving the accuracy and performance of network training.
Inventors:
YU TONG (CN)
Application Number:
PCT/CN2021/109505
Publication Date:
March 24, 2022
Filing Date:
July 30, 2021
Export Citation:
Assignee:
SUZHOU INSPUR INTELLIGENT TECH CO LTD (CN)
International Classes:
G06N3/08
Foreign References:
| CN112232508A | 2021-01-15 | |||
| CN110770764A | 2020-02-07 | |||
| US20180121814A1 | 2018-05-03 |
Other References:
TONG YU; HONG ZHU: "Hyper-Parameter Optimization: A Review of Algorithms and Applications", ARXIV.ORG, 12 March 2020 (2020-03-12), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081620036
Attorney, Agent or Firm:
LIAN & LIEN IP ATTORNEYS (CN)
Download PDF: