arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.05915cs.LGcs.AIstat.ML
收藏

瞬时故障对BNN推理加速器影响的研究

A Survey on Impact of Transient Faults on BNN Inference Accelerators

Florida Polytechnic University(佛罗里达理工大学);University of Rhode Island(罗德岛大学)

Navid Khoshavi, Connor Broyles, Yu Bi

摘要:

在过去的几年里,设计人工智能算法的哲学已经显著地转向从海量数据中自动提取可组合系统。大数据的蓬勃发展加速了这种模式的转变,使我们能够轻松访问和分析非常大的数据集。最著名的大数据分析技术被称为深度学习。这些模型需要显著的计算能力和极高的存储器访问,这需要设计新颖的方法来减少存储器访问并提高功率效率,同时考虑特定领域硬件加速器的发展以支持当前和未来的数据大小和模型结构。特定的集成电路几乎不考虑在存在软错误的情况下保持复杂神经网络计算的弹性的基本要求。软错误可能击中硬件加速器中的存储器存储或组合逻辑,这可能影响架构行为,使得结果的精度落在最小允许正确性之后。在这项研究中,我们证明了软错误对称为二值化神经网络的定制深度学习算法的影响可能会导致严重的图像错误分类。我们的实验结果表明,在最坏情况下,在故障注入期间,在CIFAR-10和MNIST数据集上,lfcW 1A 1和cnvW 1A 1网络中的图像分类器的准确率分别大幅下降了76.70%和19.25

英文摘要:

Over past years, the philosophy for designing the artificial intelligence algorithms has significantly shifted towards automatically extracting the composable systems from massive data volumes. This paradigm shift has been expedited by the big data booming which enables us to easily access and analyze the highly large data sets. The most well-known class of big data analysis techniques is called deep learning. These models require significant computation power and extremely high memory accesses which necessitate the design of novel approaches to reduce the memory access and improve power efficiency while taking into account the development of domain-specific hardware accelerators to support the current and future data sizes and model structures.The current trends for designing application-specific integrated circuits barely consider the essential requirement for maintaining the complex neural network computation to be resilient in the presence of soft errors. The soft errors might strike either memory storage or combinational logic in the hardware accelerator that can affect the architectural behavior such that the precision of the results fall behind the minimum allowable correctness. In this study, we demonstrate that the impact of soft errors on a customized deep learning algorithm called Binarized Neural Network might cause drastic image misclassification. Our experimental results show that the accuracy of image classifier can drastically drop by 76.70% and 19.25% in lfcW1A1 and cnvW1A1 networks,respectively across CIFAR-10 and MNIST datasets during the fault injection for the worst-case scenarios

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑