Supervision : Haralampos STRATIGOPOULOS

Functional safety and reliability of neuromorphic computing systems

The recent rise of Artificial Intelligence (AI) has found a wide range of applications essentially integrating it gaining more and more ground in almost every field of our lives. With this steep integration of AI, it is reasonable for concerns to arise, which need to be eliminated before the employment of AI in the field, especially in mission- and safety-critical applications like autonomous vehicles. Spiking Neural Networks (SNNs), although biologically inspired, inherit only partially the remarkable fault resilience capabilities of their biological counterparts, being vulnerable to electronic defects and faults occurring at hardware level. Hence, a methodological exploration of the dependability characteristics of AI hardware accelerators and neuromorphic platforms is of utmost importance. This thesis tackles the subjects of testing and fault tolerance in SNNs and their neuromorphic implementations on hardware.

Phd defence : 06/07/2023

Jury members :

Lorena Anghel, Professeure, Grenoble INP, Spintec, Grenoble [Rapporteur]
Paolo Rech, Professeur Associé, Université Degli Studi de Trento, Italie [Rapporteur]
Bertrand Granado, Professeur, Sorbonne Université, CNRS, LIP6, Paris
Said Hamdioui, Professeur, Université Technologique de Delft, Pays-Bas
Alkiviadis Hatzopoulos, Professeur, Université Aristote de Thessalonique, Grèce
Haralampos Stratigopoulos, Directeur de Recherche, Sorbonne Université, CNRS, LIP6, Paris

2020-2024 Publications

• 2024
  • Th. Spyrou, S. Hamdioui, Haralampos‑G. Stratigopoulos : “SpikeFI: A Fault Injection Framework for Spiking Neural Networks”, (2024)
• 2023
  • Th. Spyrou : “Functional safety and reliability of neuromorphic computing systems”, thesis, phd defence 06/07/2023, supervision Stratigopoulos, Haralampos (2023)
  • Haralampos‑G. Stratigopoulos, Th. Spyrou, S. Raptis : “Testing and Reliability of Spiking Neural Networks: A Review of the State-of-the-Art”, 36^th IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT 2023), Juan-Les-Pins, France (2023)
  • Th. Spyrou, Haralampos‑G. Stratigopoulos : “On-Line Testing of Neuromorphic Hardware”, 2023 IEEE European Test Symposium (ETS), Venise, Italy, pp. 1-6, (IEEE), (ISBN: 979-8-3503-3634-4) (2023)
  • S. El‑Sayed, Th. Spyrou, L. Camuñas‑Mesa, Haralampos‑G. Stratigopoulos : “Compact Functional Testing for Neuromorphic Computing Circuits”, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 42 (7), pp. 2391-2403, (IEEE) (2023)
• 2022
  • Th. Spyrou, S. El‑Sayed, E. Afacan, L. Camuñas‑Mesa, B. Linares‑Barranco, Haralampos‑G. Stratigopoulos : “Reliability Analysis of a Spiking Neural Network Hardware Accelerator”, Design, Automation and Test in Europe Conference (DATE), Antwerp, Belgium, pp. 370-375, (IEEE) (2022)
• 2021
  • Th. Spyrou, S. El‑Sayed, E. Afacan, L. Camuñas‑Mesa, B. Linares‑Barranco, Haralampos‑G. Stratigopoulos : “Neuron Fault Tolerance in Spiking Neural Networks”, 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), Grenoble (virtuel), France, pp. 743-748, (IEEE) (2021)
• 2020
  • S. El‑Sayed, Th. Spyrou, A. Pavlidis, E. Afacan, L. Camuñas‑Mesa, B. Linares‑Barranco, Haralampos‑G. Stratigopoulos : “Spiking Neuron Hardware-Level Fault Modeling”, 2020 IEEE 26^th International Symposium on On-Line Testing and Robust System Design (IOLTS), Naples, Italy (2020)