Because deep neural networks (DNNs) rely on a large number of parameters and computations, their implementation in energy-constrained systems is challenging. In this paper, we investigate the solution of reducing the supply voltage of the memories used in the system, which results in bit-cell faults. We explore the robustness of state-of-the-art DNN architectures towards such defects and propose a regularizer meant to mitigate their effects on accuracy. Our experiments clearly demonstrate the interest of operating the system in a faulty regime to save energy without reducing accuracy.
@article{arxiv.1911.10287,
title = {Training Modern Deep Neural Networks for Memory-Fault Robustness},
author = {Ghouthi Boukli Hacene and François Leduc-Primeau and Amal Ben Soussia and Vincent Gripon and François Gagnon},
journal= {arXiv preprint arXiv:1911.10287},
year = {2019}
}