Error Analysis and Improving the Accuracy of Winograd Convolution for Deep Neural Networks

DOI10.1145/3412380zbMath1486.65285arXiv1803.10986OpenAlexW3098382995WikidataQ113309910 ScholiaQ113309910MaRDI QIDQ5066584

Kirk M. Soodhalter, Andrew A. Anderson, Barbara Barabasz, David Gregg

Publication date: 29 March 2022

Published in: ACM Transactions on Mathematical Software (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1803.10986

zbMATH Keywords

convolutionWinograd algorithmnumerical analysisfloating point errordeep neural networkToom-Cook algorithm

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Numerical methods for integral transforms (65R10)

This page was built for publication: Error Analysis and Improving the Accuracy of Winograd Convolution for Deep Neural Networks