Buch, Englisch, 131 Seiten, Format (B × H): 173 mm x 246 mm, Gewicht: 467 g
Reihe: Synthesis Lectures on Engineering, Science, and Technology
Buch, Englisch, 131 Seiten, Format (B × H): 173 mm x 246 mm, Gewicht: 467 g
Reihe: Synthesis Lectures on Engineering, Science, and Technology
ISBN: 978-3-031-18598-4
Verlag: Springer Nature Switzerland
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.
Zielgruppe
Research
Autoren/Hrsg.
Fachgebiete
- Mathematik | Informatik EDV | Informatik Angewandte Informatik
- Mathematik | Informatik EDV | Informatik Informatik Mensch-Maschine-Interaktion Ambient Intelligence, RFID, Internet der Dinge
- Technische Wissenschaften Energietechnik | Elektrotechnik Elektrotechnik
- Technische Wissenschaften Elektronik | Nachrichtentechnik Nachrichten- und Kommunikationstechnik
- Technische Wissenschaften Elektronik | Nachrichtentechnik Elektronik Bauelemente, Schaltkreise
Weitere Infos & Material
Introduction.- Background in ML Models and Radiation Effects.- Related Works.- Soft Error Assessment Methodology.- Early Soft Error Consistency Assessment.- Soft Error Reliability Assessment of ML Inference Models executing on resource-constrained IoT edge devices.- Conclusions and Future Work.