Soft Error Tolerant Convolutional Neural Networks on FPGAs With Ensemble Learning

Convolutional neural networks (CNNs) are widely used in computer vision and natural language processing. Field-programmable gate arrays (FPGAs) are popular accelerators for CNNs. However, if used in critical applications, the reliability of FPGA-based CNNs becomes a priority because FPGAs are prone...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on very large scale integration (VLSI) systems Vol. 30; no. 3; pp. 291 - 302
Main Authors: Gao, Zhen, Zhang, Han, Yao, Yi, Xiao, Jiajun, Zeng, Shulin, Ge, Guangjun, Wang, Yu, Ullah, Anees, Reviriego, Pedro
Format: Journal Article
Language:English
Published: New York IEEE 01.03.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Artificial neural networks
Computer vision
Convolution
Convolutional neural networks
Convolutional neural networks (CNNs)
ensemble
Ensemble learning
fault injection
Fault tolerant systems
Field programmable gate arrays
field-programmable gate array (FPGA) accelerator
Natural language processing
Neural networks
Random access memory
Redundancy
Reliability
Reliability analysis
Robustness
soft error tolerance
Soft errors
System reliability
Systems analysis
ISSN:1063-8210, 1557-9999
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Convolutional neural networks (CNNs) are widely used in computer vision and natural language processing. Field-programmable gate arrays (FPGAs) are popular accelerators for CNNs. However, if used in critical applications, the reliability of FPGA-based CNNs becomes a priority because FPGAs are prone to suffer soft errors. Traditional protection schemes, such as triple modular redundancy (TMR), introduce a large overhead, which is not acceptable in resource-limited platforms. This article proposes to use an ensemble of weak CNNs to build a robust classifier with low cost. To have a group of base CNNs with low complexity and balanced similarity and diversity, residual neural networks (ResNets) with different layers (20/32/44/56) are combined in the ensemble system to replace a single strong ResNet 110. In addition, a robust combiner is designed based on the reliability evaluation of a single ResNet. Single ResNets with different layers and different ensemble schemes are implemented on the FPGA accelerator based on Xilinx Zynq 7000 SoC. The reliability of the ensemble systems is evaluated based on a large-scale fault injection platform and compared with that of the TMR-protected ResNet 110 and ResNet 20. Experiment results show that the proposed ensembles could effectively improve the system reliability when suffering soft errors with an overhead much lower than TMR.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1063-8210
1557-9999
DOI:10.1109/TVLSI.2021.3138491