A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
Emulating the Effects of Radiation-Induced Soft-Errors for the Reliability Assessment of Neural Networks (2022)
Matanaluza, L., Ruospo, A., Söderström, D., Cazzaniga, C., Kastriotou, M., Sanchez, E., Bosio, A., & Dilillo, L. (2022). Emulating the Effects of Radiation-Induced Soft-Errors for the Reliability Assessment of Neural Networks. IEEE Transactions on Emerging Topics in Computing, 10(4), 1867-1882. https://doi.org/10.1109/TETC.2021.3116999
JYU-tekijät tai -toimittajat
Julkaisun tiedot
Julkaisun kaikki tekijät tai toimittajat: Matanaluza, Lucas; Ruospo, Annachiara; Söderström, Daniel; Cazzaniga, Carlo; Kastriotou, Maria; Sanchez, Ernesto; Bosio, Alberto; Dilillo, Luigi
Lehti tai sarja: IEEE Transactions on Emerging Topics in Computing
ISSN: 2376-4562
eISSN: 2168-6750
Julkaisuvuosi: 2022
Volyymi: 10
Lehden numero: 4
Artikkelin sivunumerot: 1867-1882
Kustantaja: Institute of Electrical and Electronics Engineers (IEEE)
Julkaisumaa: Yhdysvallat (USA)
Julkaisun kieli: englanti
DOI: https://doi.org/10.1109/TETC.2021.3116999
Julkaisun avoin saatavuus: Ei avoin
Julkaisukanavan avoin saatavuus:
Julkaisu on rinnakkaistallennettu (JYX): https://jyx.jyu.fi/handle/123456789/85322
Tiivistelmä
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).
Vapaat asiasanat: neural nets; reliability; approximate methods; fault injection; radiation effects
Liittyvät organisaatiot
Hankkeet, joissa julkaisu on tehty
- Radiation and Reliability Challenges for Electronics Used in Space, Aviation, Ground and Accelerators
- Virtanen, Ari
- Euroopan komissio
OKM-raportointi: Kyllä
Raportointivuosi: 2022
JUFO-taso: 1