Conference Papers Year : 2025

STDP-Trained Spiking Neural Network Reliability Assessment Through Fault Injections

Abstract

Spiking Neural Networks (SNNs) offer a promising computing paradigm suitable for low-power artificial intelligence. Spike-Timing Dependent Plasticity (STDP) is an unsupervised, biologically-inspired learning rule for SNNs. This work studies the reliability of STDP-trained SNNs under hardware faults which is largely unexplored. We present a thorough fault injection analysis of an STDP-trained SNN designed in Brian 2 simulator for MNIST classification. The analysis introduces faults in neurons and synapses before, during, and after training. We consider both permanent and transient, as well as single and multiple faults. We identify cases where the SNN exhibits inherent fault tolerance, cases where it adapts to faults through training, and cases where fault tolerance mechanisms are required.

Fichier principal
Vignette du fichier
STDP_Trained_Spiking_Neural_Network_Reliability_Assessment_Through_Fault_Injections(2).pdf (876.72 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Licence

Dates and versions

hal-05083335 , version 1 (24-05-2025)

Licence

Identifiers

  • HAL Id : hal-05083335 , version 1

Cite

Zalfa Jouni, Haralampos-G. Stratigopoulos. STDP-Trained Spiking Neural Network Reliability Assessment Through Fault Injections. 31st IEEE International Symposium on On-Line Testing and Robust System Design, Jul 2025, Ischia, Italy. ⟨hal-05083335⟩
989 View
358 Download

Share

  • More