2020 · 22 citations · 11 references
ComputingComputer ScienceArtificial IntelligenceKnowledge RepresentationMachine LearningDeep LearningExpert SystemsNeural NetworksPattern RecognitionRule-based RepresentationDomain Knowledge ExtractionExplorationRandom SamplingRule ExtractionRule LearningRule MiningRule-based SystemsSoftware Process Automation
Deep neural networks (DNNs) have been widely applied in the software development process to automatically learn patterns from massive data. However, many applications still make decisions based on rules that are manually crafted and verified by domain experts due to safety or security concerns. In this paper, we aim to close the gap between DNNs and rule-based systems by automating the rule generation process via extracting knowledge from well-trained DNNs. Existing techniques with similar purposes either rely on specific DNNs input instances or use inherently unstable random sampling of the input space. Therefore, these approaches either limit the exploration area to a local decision-space of the DNNs or fail to converge to a consistent set of rules. The resulting rules thus lack representativeness and stability.
11
Techniques for interpretable machine learning
Mengnan Du, Ninghao Liu, Xia Hu · Communications of the ACM · 2019 · 1.2K citations
Kevin Allix, Tegawendé F. Bissyandé, Jacques Klein et al. · 2016 · 787 citations · Full text
IoT Security: Ongoing Challenges and Research Opportunities
Zhikai Zhang, Michael Cheng Yi Cho, Chia‐Wei Wang et al. · 2014 · 721 citations
DroidMat: Android Malware Detection through Manifest and API Calls Tracing
Dong-Jie Wu, Ching-Hao Mao, Te-En Wei et al. · 2012 · 629 citations