Multiple-boundary clustering and prioritization to promote neural network retraining
Weijun Shen, Yanhui Li, Lin Chen, Yuanlei Han, Yuming Zhou, Baowen Xu
Abstract
With the increasing application of deep learning (DL) models in many safety-critical scenarios, effective and efficient DL testing techniques are much in demand to improve the quality of DL models. One of the major challenges is the data gap between the training data to construct the models and the testing data to evaluate them. To bridge the gap, testers aim to collect an effective subset of inputs from the testing contexts, with limited labeling effort, for retraining DL models.
Topics & Concepts
RetrainingComputer scienceBridge (graph theory)Artificial intelligenceCluster analysisMachine learningPrioritizationConstruct (python library)Data modelingArtificial neural networkDeep learningQuality (philosophy)Data miningEngineeringDatabaseInternal medicineBusinessManagement scienceEpistemologyProgramming languageMedicinePhilosophyInternational tradeAdversarial Robustness in Machine LearningAnomaly Detection Techniques and ApplicationsMachine Learning and Data Classification