Analyzing the reliability of convolutional neural networks on GPUs : GoogLeNet as a case study

Ibrahim, Younis Mohammed and Wang, Haibin and Khalid, Adam (2020) Analyzing the reliability of convolutional neural networks on GPUs : GoogLeNet as a case study. In: 2020 International Conference on Computing and Information Technology, ICCIT 2020. 2020 International Conference on Computing and Information Technology, ICCIT 2020 , 9 - 10 September 2020 , Tabuk. pp. 1-6. (9213804). ISBN 978-172812680-7 (Published)

	Pdf Analyzing the reliability of convolutional neural networks on GPUs.pdf Restricted to Repository staff only Download (2MB) | Request a copy
Preview	Pdf Analyzing the reliability of convolutional neural networks on GPUs_GoogLeNet as a case study_ABS.pdf Download (166kB) | Preview

Abstract

Convolutional Neural Networks (CNNs) are used for tasks such as object recognition. Once a CNN model is used in a radiative environment, reliability of the system against soft errors is a crucial issue, especially in safety-critical and high-performance applications that bound with real-time response. Selectively-hardening techniques do improve the reliability of these systems. However, the hard question in selective techniques is "how to exclusively select code portions to harden, to safe the performance from being degraded". In this paper, we propose a comprehensive analysis methodology for CNN-based classification models to confidently determine the only vulnerable parts of the source code. To achieve this, we propose a technique, Layer Vulnerability Factor (LVF) and adopt another technique, Kernel Vulnerability Factor (KVF). We apply these techniques to GoogLeNet, which is a famous image classification model, to validate our methodology. We precisely identify the parts of the GoogLeNet model that need to be hardened instead of using expensive duplication solutions.

Item Type:	Conference or Workshop Item (Lecture)
Additional Information:	Indexed by Scopus
Uncontrolled Keywords:	Convolutional neural networks; GoogLeNet; GPUs; Reliability; Soft errors
Subjects:	T Technology > T Technology (General) T Technology > TA Engineering (General). Civil engineering (General) T Technology > TK Electrical engineering. Electronics Nuclear engineering
Faculty/Division:	Institute of Postgraduate Studies Faculty of Electrical and Electronic Engineering Technology
Depositing User:	Mr Muhamad Firdaus Janih@Jaini
Date Deposited:	02 Dec 2024 01:12
Last Modified:	02 Dec 2024 01:12
URI:	http://umpir.ump.edu.my/id/eprint/42444
Download Statistic:	View Download Statistics

Actions (login required)

View Item