Analyzing the reliability of convolutional neural networks on GPUs : GoogLeNet as a case study
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 respons...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English English |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2020
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/42444/ http://umpir.ump.edu.my/id/eprint/42444/1/Analyzing%20the%20reliability%20of%20convolutional%20neural%20networks%20on%20GPUs.pdf http://umpir.ump.edu.my/id/eprint/42444/2/Analyzing%20the%20reliability%20of%20convolutional%20neural%20networks%20on%20GPUs_GoogLeNet%20as%20a%20case%20study_ABS.pdf |
| _version_ | 1848826612650344448 |
|---|---|
| author | Ibrahim, Younis Mohammed Wang, Haibin Khalid, Adam |
| author_facet | Ibrahim, Younis Mohammed Wang, Haibin Khalid, Adam |
| author_sort | Ibrahim, Younis Mohammed |
| building | UMP Institutional Repository |
| collection | Online Access |
| description | 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. |
| first_indexed | 2025-11-15T03:47:35Z |
| format | Conference or Workshop Item |
| id | ump-42444 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English English |
| last_indexed | 2025-11-15T03:47:35Z |
| publishDate | 2020 |
| publisher | Institute of Electrical and Electronics Engineers Inc. |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-424442024-12-02T01:12:45Z http://umpir.ump.edu.my/id/eprint/42444/ Analyzing the reliability of convolutional neural networks on GPUs : GoogLeNet as a case study Ibrahim, Younis Mohammed Wang, Haibin Khalid, Adam T Technology (General) TA Engineering (General). Civil engineering (General) TK Electrical engineering. Electronics Nuclear engineering 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. Institute of Electrical and Electronics Engineers Inc. 2020-09-09 Conference or Workshop Item PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/42444/1/Analyzing%20the%20reliability%20of%20convolutional%20neural%20networks%20on%20GPUs.pdf pdf en http://umpir.ump.edu.my/id/eprint/42444/2/Analyzing%20the%20reliability%20of%20convolutional%20neural%20networks%20on%20GPUs_GoogLeNet%20as%20a%20case%20study_ABS.pdf 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) https://doi.org/10.1109/ICCIT-144147971.2020.9213804 |
| spellingShingle | T Technology (General) TA Engineering (General). Civil engineering (General) TK Electrical engineering. Electronics Nuclear engineering Ibrahim, Younis Mohammed Wang, Haibin Khalid, Adam Analyzing the reliability of convolutional neural networks on GPUs : GoogLeNet as a case study |
| title | Analyzing the reliability of convolutional neural networks on GPUs : GoogLeNet as a case study |
| title_full | Analyzing the reliability of convolutional neural networks on GPUs : GoogLeNet as a case study |
| title_fullStr | Analyzing the reliability of convolutional neural networks on GPUs : GoogLeNet as a case study |
| title_full_unstemmed | Analyzing the reliability of convolutional neural networks on GPUs : GoogLeNet as a case study |
| title_short | Analyzing the reliability of convolutional neural networks on GPUs : GoogLeNet as a case study |
| title_sort | analyzing the reliability of convolutional neural networks on gpus : googlenet as a case study |
| topic | T Technology (General) TA Engineering (General). Civil engineering (General) TK Electrical engineering. Electronics Nuclear engineering |
| url | http://umpir.ump.edu.my/id/eprint/42444/ http://umpir.ump.edu.my/id/eprint/42444/ http://umpir.ump.edu.my/id/eprint/42444/1/Analyzing%20the%20reliability%20of%20convolutional%20neural%20networks%20on%20GPUs.pdf http://umpir.ump.edu.my/id/eprint/42444/2/Analyzing%20the%20reliability%20of%20convolutional%20neural%20networks%20on%20GPUs_GoogLeNet%20as%20a%20case%20study_ABS.pdf |