A Low-cost Fault Corrector for Deep Neural Networks through Range Restriction
A Low-cost Fault Corrector for Deep Neural Networks through Range Restriction
复制标题
通过范围限制的深度神经网络低成本故障校正器
DOI：
10.1109/dsn48987.2021.00018
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
K. Pattabiraman
中科院分区：
文献类型：
--
作者：
Zitao Chen;Guanpeng Li;K. Pattabiraman
深度神经网络（DNN）在安全关键领域的采用引起了严重的可靠性问题。一个突出的例子是硬件瞬态故障，由于技术的不断扩展，这些故障的频率越来越高，并可能导致DNN的故障。这项工作提出了游侠，一个低成本的故障校正器，它直接纠正故障输出由于瞬态故障，而无需重新计算。DNN对良性故障（不会导致输出损坏）具有固有的弹性，但对严重故障（可能导致错误输出）没有弹性。Ranger是一种自动转换，用于选择性地限制DNN中的值范围，从而减少由关键故障引起的大偏差，并将其转换为DNN固有弹性可以容忍的良性故障。我们对8个DNN的评估表明，Ranger显着提高了DNN的错误恢复能力（3倍至50倍），而准确性没有损失，开销可以忽略不计。
The adoption of deep neural networks (DNNs) in safety-critical domains has engendered serious reliability concerns. A prominent example is hardware transient faults that are growing in frequency due to the progressive technology scaling, and can lead to failures in DNNs. This work proposes Ranger, a low-cost fault corrector, which directly rectifies the faulty output due to transient faults without re-computation. DNNs are inherently resilient to benign faults (which will not cause output corruption), but not to critical faults (which can result in erroneous output). Ranger is an automated transformation to selectively restrict the value ranges in DNNs, which reduces the large deviations caused by critical faults and transforms them to benign faults that can be tolerated by the inherent resilience of the DNNs. Our evaluation on 8 DNNs demonstrates Ranger significantly increases the error resilience of the DNNs (by 3x to 50x), with no loss in accuracy, and with negligible overheads.
CNN 的就地零空间内存保护
DOI：
--
发表时间：
2019
期刊：
Neural Information Processing Systems 2019
影响因子：
--
作者：
Guan, Hui;Ning, Lin;Lin, Zhen;Shen, Xipeng;Zhou, Huiyang;Lim, Seung-Hwan
通讯作者：
Lim, Seung-Hwan