Back to Search
Start Over
Emulating the Effects of Radiation-Induced Soft-Errors for the Reliability Assessment of Neural Networks
- Source :
- IEEE Transactions on Emerging Topics in Computing, IEEE Transactions on Emerging Topics in Computing, Institute of Electrical and Electronics Engineers, In press, pp.1-1. ⟨10.1109/TETC.2021.3116999⟩
- Publication Year :
- 2022
- Publisher :
- Institute of Electrical and Electronics Engineers (IEEE), 2022.
-
Abstract
- International audience; Convolutional Neural Networks (CNNs) are currently one of the most widely used predictive models in machine learning. Recent studies have demonstrated that hardware faults induced by radiation fields, including cosmic rays, may significantly impact the CNN inference leading to wrong predictions. Therefore, ensuring the reliability of CNNs is crucial, especially for safety-critical systems. In the literature, several works propose reliability assessments of CNNs mainly based on statistically injected faults. This work presents a software emulator capable of injecting real faults retrieved from radiation tests. Specifically, from the device characterisation of a DRAM memory, we extracted event rates and fault models. The software emulator can reproduce their incidence and access their effect on CNN applications with a reliability assessment precision close to the physical one. Radiation-based physical injections and emulator-based injections are performed on three CNNs (LeNet-5) exploiting different data representations. Their outcomes are compared, and the software results evidence that the emulator is able to reproduce the faulty behaviours observed during the radiation tests for the targeted CNNs. This approach leads to a more concise use of radiation experiments since the extracted fault models can be reused to explore different scenarios (e.g., impact on a different application).
- Subjects :
- fault injection
Computer science
Neural nets
Inference
Radiation effects
Radiation induced
Fault (power engineering)
Convolutional neural network
Software
Fault injection
Computer Science (miscellaneous)
[SPI.NANO]Engineering Sciences [physics]/Micro and nanotechnologies/Microelectronics
Reliability (statistics)
reliability
Artificial neural network
Approximate methods
Event (computing)
business.industry
Reliability
Computer Science Applications
[SPI.TRON]Engineering Sciences [physics]/Electronics
Human-Computer Interaction
neural nets
Computer engineering
approximate methods
radiation effects
[INFO.INFO-ES]Computer Science [cs]/Embedded Systems
business
Information Systems
Subjects
Details
- Language :
- English
- ISSN :
- 21686750
- Database :
- OpenAIRE
- Journal :
- IEEE Transactions on Emerging Topics in Computing, IEEE Transactions on Emerging Topics in Computing, Institute of Electrical and Electronics Engineers, In press, pp.1-1. ⟨10.1109/TETC.2021.3116999⟩
- Accession number :
- edsair.doi.dedup.....92ce93a1d8750deeb0a9765f433053e1
- Full Text :
- https://doi.org/10.1109/TETC.2021.3116999⟩