Work

Reliability of Deep Neural Networks: Impact and Open Issues

Year: 2025

Type: article

Abstract: Editor’s notes: This article introduces a statistical fault injection approach to evaluate the resilience of deep-neural-network applications against permanent faults in synaptic weights, while also discussing open challenges and emerging trends. —Jyotika Athavale, Synopsys, USA —Haralampos-G. Stratigopoulos, Sorbonne Université, CNRS, LIP6, France

Source: IEEE Design and Test

DOI: 10.1109/mdat.2025.3544125

Authors: Annachiara Ruospo, Salvatore Pappalardo, Vittorio Turco, Alberto Bosio, Ernesto Sanchez