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.
Produkteigenschaften
- Artikelnummer: 9783031186011
- Medium: Buch
- ISBN: 978-3-031-18601-1
- Verlag: Springer International Publishing
- Erscheinungstermin: 03.01.2024
- Sprache(n): Englisch
- Auflage: 1. Auflage 2023
- Serie: Synthesis Lectures on Engineering, Science, and Technology
- Produktform: Kartoniert
- Gewicht: 261 g
- Seiten: 131
- Format (B x H x T): 168 x 240 x 9 mm
- Ausgabetyp: Kein, Unbekannt