arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.06320cs.SEcs.LG
收藏

改进深度学习测试

Towards Improved Testing For Deep Learning

University of Virginia(弗吉尼亚大学)

Jasmine Sekhon, Cody Fleming

摘要:

深度神经网络在安全关键型应用中的使用越来越多,这使得有必要在实际使用之前进行充分的测试,以检测和纠正极端情况输入的任何不正确行为。深度神经网络缺乏显式的控制流结构,因此无法对其应用传统的软件测试标准,如代码覆盖率。在本文中,我们研究了深度神经网络的现有测试方法,改进的机会以及对快速,可扩展,可推广的端到端测试方法的需求。我们还提出了一个深度神经网络的覆盖标准,试图捕捉深度神经网络逻辑的所有可能部分。

英文摘要:

The growing use of deep neural networks in safety-critical applications makes it necessary to carry out adequate testing to detect and correct any incorrect behavior for corner case inputs before they can be actually used. Deep neural networks lack an explicit control-flow structure, making it impossible to apply to them traditional software testing criteria such as code coverage. In this paper, we examine existing testing methods for deep neural networks, the opportunities for improvement and the need for a fast, scalable, generalizable end-to-end testing method. We also propose a coverage criterion for deep neural networks that tries to capture all possible parts of the deep neural network's logic.

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。

↑