测试自旋电子学实现的基于 Monte Carlo Dropout 的贝叶斯神经网络
Testing Spintronics Implemented Monte Carlo Dropout-Based Bayesian Neural Networks
AI总结：
本文首次提出自旋电子学 Dropout 模块非理想性模型，并设计基于可重复性排序的测试框架，仅用 0.2% 训练数据即实现 100% 故障覆盖率，保障贝叶斯神经网络可靠性。
摘要：
贝叶斯神经网络（BayNNs）能够固有地估计预测不确定性，从而促进知情决策。基于 Dropout 的 BayNNs 越来越多地被实现于基于自旋电子学的存内计算架构中，以适用于资源受限但高性能的安全关键应用。尽管不确定性估计很重要，但 Dropout 生成和 BayNN 计算的可靠性对目标应用同样重要，却在现有工作中被忽视。然而，由于其随机性，测试 BayNNs 比传统神经网络更具挑战性。本文首次提出了基于自旋电子学的 Dropout 模块非理想性模型，并分析了其对不确定性估计和准确性的影响。此外，我们提出了一种基于可重复性排序的测试框架，适用于基于 Dropout 的 BayNN，在仅使用 0.2% 训练数据作为测试向量的情况下，实现高达 100% 的故障覆盖率。
英文摘要：
Bayesian Neural Networks (BayNNs) can inherently estimate predictive uncertainty, facilitating informed decision-making. Dropout-based BayNNs are increasingly implemented in spintronics-based computation-in-memory architectures for resource-constrained yet high-performance safety-critical applications. Although uncertainty estimation is important, the reliability of Dropout generation and BayNN computation is equally important for target applications but is overlooked in existing works. However, testing BayNNs is significantly more challenging compared to conventional NNs, due to their stochastic nature. In this paper, we present for the first time the model of the non-idealities of the spintronics-based Dropout module and analyze their impact on uncertainty estimates and accuracy. Furthermore, we propose a testing framework based on repeatability ranking for Dropout-based BayNN with up to $100\%$ fault coverage while using only $0.2\%$ of training data as test vectors.
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。
