Analyzing and increasing the reliability of convolutional neural networks on GPUs

FF dos Santos, PF Pimenta, C Lunardi… - IEEE Transactions …, 2018 - ieeexplore.ieee.org
Graphics processing units (GPUs) are playing a critical role in convolutional neural networks
(CNNs) for image detection. As GPU-enabled CNNs move into safety-critical environments …

Artificial neural networks for space and safety-critical applications: Reliability issues and potential solutions

P Rech - IEEE Transactions on Nuclear Science, 2024 - ieeexplore.ieee.org
Machine learning is among the greatest advancements in computer science and
engineering and is today used to classify or detect objects, a key feature in autonomous …

A Survey on Failure Analysis and Fault Injection in AI Systems

G Yu, G Tan, H Huang, Z Zhang, P Chen… - arxiv preprint arxiv …, 2024 - arxiv.org
The rapid advancement of Artificial Intelligence (AI) has led to its integration into various
areas, especially with Large Language Models (LLMs) significantly enhancing capabilities …

Soft error effects on arm microprocessors: Early estimations versus chip measurements

PR Bodmann, G Papadimitriou… - IEEE Transactions …, 2021 - ieeexplore.ieee.org
Extensive research efforts are being carried out to evaluate and improve the reliability of
computing devices either through beam experiments or simulation-based fault injection …

Resiliency of automotive object detection networks on GPU architectures

A Lotfi, S Hukerikar, K Balasubramanian… - 2019 IEEE …, 2019 - ieeexplore.ieee.org
Safety is the most important aspect of an autonomous driving platform. Deep neural
networks (DNNs) play an increasingly critical role in localization, perception, and control in …

Revealing gpus vulnerabilities by combining register-transfer and software-level fault injection

FF dos Santos, JER Condia, L Carro… - 2021 51st Annual …, 2021 - ieeexplore.ieee.org
The complexity of both hardware and software makes GPUs reliability evaluation extremely
challenging. A low level fault injection on a GPU model, despite being accurate, would take …

A selective mitigation technique of soft errors for dnn models used in healthcare applications: Densenet201 case study

K Adam, II Mohamed, Y Ibrahim - IEEE Access, 2021 - ieeexplore.ieee.org
Deep neural networks (DNNs) have been successfully deployed in widespread domains,
including healthcare applications. DenseNet201 is a new DNN architecture used in …

Experimental and analytical study of xeon phi reliability

D Oliveira, L Pilla, N DeBardeleben… - Proceedings of the …, 2017 - dl.acm.org
We present an in-depth analysis of transient faults effects on HPC applications in Intel Xeon
Phi processors based on radiation experiments and high-level fault injection. Besides …

Reliability evaluation of mixed-precision architectures

FF dos Santos, C Lunardi, D Oliveira… - … Symposium on High …, 2019 - ieeexplore.ieee.org
Novel computing architectures offer the possibility to execute float point operations with
different precisions. The execution of reduced precision operations, when acceptable for …

Combining architectural simulation and software fault injection for a fast and accurate CNNs reliability evaluation on GPUs

JER Condia, FF dos Santos… - 2021 IEEE 39th VLSI …, 2021 - ieeexplore.ieee.org
Graphic Processing Units (GPUs) are commonly used to accelerate Convolutional Neural
Networks (CNNs) for object detection and classification. As CNNs are employed in safety …