A Reliability Study on CNNs for Critical Embedded Systems - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

A Reliability Study on CNNs for Critical Embedded Systems

Résumé

Deep learning systems such as Convolutional Neural Networks (CNNs) have shown remarkable efficiency in dealing with a variety of complex real life problems. To accelerate the execution of these heavy algorithms, a plethora of software implementations and hardware accelerators have been proposed. In a context of shrinking devices dimensions, reliability issues of CNN-hosting systems are under-explored. In this paper, we experimentally evaluate the inherent fault tolerance of CNNs by injecting errors within network modules, namely processing elements and memories. Our experiments demonstrate a non uniform sensitivity between different parts of the system. While CNNs are relatively resilient to errors occurring in processing elements, transient faults hitting memories lead to catastrophic degradation of accuracy.
Fichier non déposé

Dates et versions

hal-03430208 , version 1 (16-11-2021)

Identifiants

Citer

Mohamed Ayoub Neggaz, Pablo Ribalta, Ihsen Alouani, Smail Niar. A Reliability Study on CNNs for Critical Embedded Systems. 2018 IEEE 36th International Conference on Computer Design (ICCD), Oct 2018, Orlando, United States. pp.476-479, ⟨10.1109/ICCD.2018.00077⟩. ⟨hal-03430208⟩
12 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More