Patent · US Active

Fast computation of a convolutional neural network

US10635951B1 · kind B1 · utility

3Cited by

0References

17Claims

0Family size

Assignee

Alibaba Group Holding Limited · KY

Inventors

Yongchao Liu · Jiaocheng District, CN
Qiyin Huang · Hangzhou City, CN
Guozhen Pan · Hangzhou City, CN
Sizhong Li · Hangzhou City, CN
Jianguo Xu · Newton, US
Haitao Zhang · Ithaca, US
Lin Wang · Nanhu, CN

Key dates

Filing date	Apr 22, 2019
Grant date	Apr 28, 2020
Priority date	—
Expiry date	Apr 22, 2039

Classification

Technology area (CPC G)Physics
CPC primaryG06V30/19173
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A computer-implemented method includes obtaining a trained convolutional neural network comprising one or more convolutional layers, each of the one or more convolutional layers comprising a plurality of filters with known filter parameters; pre-computing a reusable factor for each of the one or more convolutional layers based on the known filter parameters of the trained convolutional neural network; receiving input data to the trained convolutional neural network; computing an output of the each of the one or more convolutional layers using a Winograd convolutional operator based on the pre-computed reusable factor and the input data; and determining output data of the trained convolutional network based on the output of the each of the one or more convolutional layers.

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