Soft Error Resilience of Deep Residual Networks for Object Recognition
Convolutional Neural Networks (CNNs) have truly gained attention in object recognition and object classification in particular. When being implemented on Graphics Processing Units (GPUs), deeper networks are more accurate than shallow ones. Residual Networks (ResNets) are one of the deepest CNN arch...
Main Authors: | Younis Ibrahim, Haibin Wang, Man Bai, Zhi Liu, Jianan Wang, Zhiming Yang, Zhengming Chen |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8963961/ |
Similar Items
-
A Selective Mitigation Technique of Soft Errors for DNN Models Used in Healthcare Applications: DenseNet201 Case Study
by: Khalid Adam, et al.
Published: (2021-01-01) -
Prediction-Based Error Correction for GPU Reliability with Low Overhead
by: Hyunyul Lim, et al.
Published: (2020-11-01) -
EBSCN: An Error Backtracking Method for Soft Errors Based on Clustering and a Neural Network
by: Nan Zhang, et al.
Published: (2019-01-01) -
Characterizing System-Level Masking Effects against Soft Errors
by: Yohan Ko
Published: (2021-09-01) -
Selective Code Duplication for Soft Error Protection on VLIW Architectures
by: Yohan Ko, et al.
Published: (2021-07-01)