Revisiting neuron coverage metrics and quality of deep neural networks

• المؤلفون الرئيسيون: YANG, Zhou, SHI, Jieke, ASYROFI, Muhammad Hilmi, LO, David
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2022
• الموضوعات: Deep learning testing; Coverage-driven testing; Software quality; Software Engineering
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/7625; https://ink.library.smu.edu.sg/context/sis_research/article/8628/viewcontent/378600a408.pdf
• المؤسسة: Singapore Management University

Deep neural networks (DNN) have been widely applied in modern life, including critical domains like autonomous driving, making it essential to ensure the reliability and robustness of DNN-powered systems. As an analogy to code coverage metrics for testing conventional software, researchers have prop...