Patent · US Active

Method and apparatus for adapting parameters of neural network

US11461632B2 · kind B2 · utility

0Cited by

2References

18Claims

0Family size

Assignee

Nanjing Horizon Robotics Technology Co., Ltd. · CN

Inventors

Kun Ling · Beijing, CN
Liang Chen · Dalian, CN
Jianjun Li · Beijing, CN
Delin Li · Canton, US
Chang Huang · Beijing, CN

Key dates

Filing date	Apr 23, 2018
Grant date	Oct 4, 2022
Priority date	—
Expiry date	Aug 5, 2041

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/063
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Disclosed are a method and an apparatus for adapting parameters of a neural network. The method includes selecting one or more dimensions for a weight parameter of each of at least one layer of the neural network, determining a dimension value and a corresponding target value in each dimension of the weight parameter, and padding the weight parameter in a case where the dimension value in at least one dimension of the weight parameter is less than the corresponding target value, the dimension value in each dimension of the weight parameter after the padding being equal to the corresponding target value.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.