公开(公告)号：US20230092453A1

公开(公告)日：2023-03-23

申请号：US17993436

申请日：2022-11-23

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Zidong Wang ,  Mengyun Chen ,  Fan Yu ,  Lei Chen

IPC: G06N3/04 ,  G06V10/774 ,  G06V20/58

Abstract: The present disclosure relates to parameter updating methods. In one example method, a parameter in a neural network model is updated for a plurality of times through a plurality of iterations. The plurality of iterations include a first iteration period and a second iteration period. In the first iteration period, an inverse matrix of an additional matrix of the neural network model is updated once based on a quantity of iterations indicated by a first update stride. In the second iteration period, the inverse matrix of the additional matrix of the neural network model is updated once based on a quantity of iterations indicated by a second update stride, where the first iteration of the second iteration period is after the last iteration of the first iteration period in an iteration sequence, and the second update stride is greater than the first update stride.