Adaptive test selection for deep neural networks
Xinyu Gao, Yang Feng, Yining Yin, Zixi Liu, Zhenyu Chen, Baowen Xu
Abstract
Deep neural networks (DNN) have achieved tremendous development in the past decade. While many DNN-driven software applications have been deployed to solve various tasks, they could also produce incorrect behaviors and result in massive losses. To reveal the incorrect behaviors and improve the quality of DNN-driven applications, developers often need rich labeled data for the testing and optimization of DNN models. However, in practice, collecting diverse data from application scenarios and labeling them properly is often a highly expensive and time-consuming task.
Topics & Concepts
Computer scienceTask (project management)Artificial neural networkDeep neural networksSelection (genetic algorithm)Artificial intelligenceMachine learningSoftwareDeep learningQuality (philosophy)EngineeringSystems engineeringPhilosophyProgramming languageEpistemologySoftware Testing and Debugging TechniquesAdversarial Robustness in Machine LearningAnomaly Detection Techniques and Applications