Patent · US Active

Deep learning model embodiments and training embodiments for faster training

US11144790B2 · kind B2 · utility

1Cited by

0References

20Claims

0Family size

Assignee

BAIDU USA LLC · US

Inventors

Baopu Li · Santa Clara, US
Zhiyu Cheng · Sunnyvale, US
Yingze Bao · Beijing, CN

Key dates

Filing date	Oct 11, 2019
Grant date	Oct 12, 2021
Priority date	—
Expiry date	Dec 31, 2039

Classification

Technology area (CPC G)Physics
CPC primaryG06V10/82
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Presented herein are embodiments of a training deep learning models. In one or more embodiments, a compact deep learning model comprises fewer layers, which require fewer floating-point operations (FLOPs). Presented herein are also embodiments of a new learning rate function, which can adaptively change the learning rate between two linear functions. In one or more embodiments, combinations of half-precision floating point format training together with larger batch size in the training process may also be employed to aid the training process.

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