LGMLNov 23, 2019

Training Modern Deep Neural Networks for Memory-Fault Robustness

arXiv:1911.10287v130 citations
Originality Incremental advance
AI Analysis

This addresses energy efficiency for DNN deployment in resource-limited hardware, but is incremental as it builds on existing robustness techniques.

The paper tackles the problem of deep neural networks being vulnerable to memory bit-cell faults caused by reduced supply voltage in energy-constrained systems, and proposes a regularizer that maintains accuracy while enabling energy savings, with experiments showing no reduction in accuracy.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes