Visible to the public Neuron Fault Tolerance in Spiking Neural Networks

TitleNeuron Fault Tolerance in Spiking Neural Networks
Publication TypeConference Paper
Year of Publication2021
AuthorsSpyrou, Theofilos, El-Sayed, Sarah A., Afacan, Engin, Camuñas-Mesa, Luis A., Linares-Barranco, Bernabé, Stratigopoulos, Haralampos-G.
Conference Name2021 Design, Automation & Test in Europe Conference & Exhibition (DATE)
Date Publishedfeb
Keywordsfault detection, Fault tolerance, Fault tolerant systems, Hardware, Mission critical systems, neural network resiliency, Neurons, Planning, pubcrawl, resilience, Resiliency
AbstractThe error-resiliency of Artificial Intelligence (AI) hardware accelerators is a major concern, especially when they are deployed in mission-critical and safety-critical applications. In this paper, we propose a neuron fault tolerance strategy for Spiking Neural Networks (SNNs). It is optimized for low area and power overhead by leveraging observations made from a large-scale fault injection experiment that pinpoints the critical fault types and locations. We describe the fault modeling approach, the fault injection framework, the results of the fault injection experiment, the fault-tolerance strategy, and the fault-tolerant SNN architecture. The idea is demonstrated on two SNNs that we designed for two SNN-oriented datasets, namely the N-MNIST and IBM's DVS128 gesture datasets.
Citation Keyspyrou_neuron_2021