Physical Sciences and Mathematics Commons^™

Ft-Cnn: Algorithm-Based Fault Tolerance For Convolutional Neural Networks, Kai Zhao, Sheng Di, Sihuan Li, Xin Liang, For Full List Of Authors, See Publisher's Website.

Computer Science Faculty Research & Creative Works

Convolutional neural networks (CNNs) are becoming more and more important for solving challenging and critical problems in many fields. CNN inference applications have been deployed in safety-critical systems, which may suffer from soft errors caused by high-energy particles, high temperature, or abnormal voltage. Of critical importance is ensuring the stability of the CNN inference process against soft errors. Traditional fault tolerance methods are not suitable for CNN inference because error-correcting code is unable to protect computational components, instruction duplication techniques incur high overhead, and existing algorithm-based fault tolerance (ABFT) techniques cannot protect all convolution implementations. In this paper, we focus …