Testing for Multiple Faults in Deep Neural Networks.

IEEE Des. Test(2024)

引用 0|浏览8
暂无评分
摘要
Deep Neural Networks (DNNs) implemented on hardware accelerators are vulnerable to various faults. This necessitates the development of efficient testing methodologies to detect them in DNN accelerators. In this work, we propose a test pattern generation approach to detect fault patterns in DNNs’ synaptic weight value representations at a bit level. The experimental results show that the generated test patterns provide 100% fault coverage for targeted fault patterns. Besides, a high compaction ratio was achieved over different datasets and model architectures (up to 50×), and high fault coverage (up to 99.9%) for unseen fault patterns during the test generation phase.
更多
查看译文
关键词
Deep neural networks,weight perturbations,multiple fault detection,Test pattern generation,Test compaction
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要