Synthesis Lectures on Engineering, Science, and Technology

Abich, Geancarlo; Ost, Luciano; Reis, Ricardo

This book describes an extensive and consistent soft error assessment of convolutional neural network (CNN) models from different domains through more than 14.8 million fault injections, considering different precision bit-width configurations, optimization parameters, and processor models. The authors also evaluate the relative performance, memory utilization, and soft error reliability trade-offs analysis of different CNN models considering a compiler-based technique w.r.t. traditional redundancy approaches.

Details

Published by: Springer

Publication Date: 2024-01-03

Format: Paperback

ISBN-13: 9783031186011

DOI: 10.1007/978-3-031-18599-1

Dimensions: 240cm x168cm

Pages: 131