2024/01/09 by Soyed Tuhin Ahmed, Ahmed, Soyed Tuhin, Michael Hefenbrock +7
Computer Science · Engineering · #Adversarial Robustness in Machine Learning #Emerging Technologies (cs.ET) #FOS: Computer and information sciences #Fault Detection and Control Systems #Hardware Architecture (cs.AR) #Machine Learning (cs.LG) #Radiation Effects in Electronics
paper · pdf · doi:10.48550/arxiv.2401.04744
openalex publication_date 2024/01/09 · openalex created_date 2024/01/13 · openalex updated_date 2026/07/28
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.