Method and device for performing convolution operation on neural network based on Winograd transform

Abstract

Some example embodiments may involve performing a convolution operation of a neural network based on a Winograd transform. Some example embodiments may involve a device including neural network processing circuitry that is configured to generate, by the neural network processing circuitry, a transformed input feature map by performing a Winograd transform on an input feature map, the transformed input feature map having a matrix form and including a plurality of channels; to perform, by the neural network processing circuitry, element-wise multiplications between a feature vector of the transformed input feature map and a weight vector of a transformed weight kernel obtained based on the Winograd transform; and to add, by the neural network processing circuitry, element-wise multiplicationresults, the element-wise multiplications being performed channel-by-channel with respect to the feature vector including feature values on a position in the plurality of channels of the transformedinput feature map.

Description

[0001] Cross References to Related Applications [0002] This application claims the benefit of Korean Patent Application No. 10-2019-0008603 filed with the Korean Intellectual Property Office on January 23, 2019, the disclosure of which is incorporated herein by reference in its entirety. technical field [0003] Some example embodiments of some inventive concepts may include methods, apparatuses, etc. for performing neural network convolution operations. Some example embodiments may relate to a method, an apparatus, etc. for performing a convolution operation of a Winograd transform-based neural network. Background technique [0004] A neural network refers to a computational architecture that is a model of a biological brain. As neural network technology has recently been developed, there have been numerous studies on obtaining effective information from input data based on at least one neural network model in various kinds of electronic systems. In some cases, processi...

AI Technical Summary

Problems solved by technology

In some cases, processing the convolution operation of a neural network may require a large number of operations

Images