A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is
Recent literature found that convolutional neural networks (CNN) with large filters perform well in some applications such as image semantic segmentation. ... Winograd transformation helps to reduce the number of multiplications in a convolution but suffers from numerical instability when the convolution filter size gets large. ... it can propagate more information to the outputs in a deep neural network. ...arXiv:2102.13272v1 fatcat:ubumszlwjrdalpsfy6jz2aumpe