DeepState
Zixi Liu, Yang Feng, Yining Yin, Zhenyu Chen
Abstract
Deep Neural Networks (DNN) have achieved tremendous success in various software applications. However, accompanied by outstanding effectiveness, DNN-driven software systems could also exhibit incorrect behaviors and result in some critical accidents and losses. The testing and optimization of DNN-driven software systems rely on a large number of labeled data that often require many human efforts, resulting in high test costs and low efficiency. Although plenty of coverage-based criteria have been proposed to assist in the data selection of convolutional neural networks, it is difficult to apply them on Recurrent Neural Network (RNN) models due to the difference between the working nature.
Topics & Concepts
Computer scienceConvolutional neural networkArtificial neural networkSoftwareArtificial intelligenceRecurrent neural networkMachine learningSelection (genetic algorithm)Deep neural networksDeep learningProgramming languageSoftware Testing and Debugging TechniquesAdversarial Robustness in Machine LearningMachine Learning and Data Classification