Towards Improved Testing For Deep Learning
This work tackles the problem of inadequate testing methods for deep neural networks, which is crucial for developers and users in safety-critical domains, though it appears incremental as it builds on existing testing approaches.
The paper addresses the challenge of testing deep neural networks in safety-critical applications by proposing a new coverage criterion to capture all possible parts of the network's logic, aiming to improve detection of incorrect behavior for corner case inputs.
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.