End-to-end Robustness for Sensing-Reasoning Machine Learning Pipelines. (arXiv:2003.00120v4 [cs.LG] UPDATED)

Intensive algorithmic efforts have been made to enable the rapid improvements
of certificated robustness for complex ML models recently. However, current
robustness certification methods are only able to certify under a limited
perturbation radius. Given that existing pure data-driven statistical
approaches have reached a bottleneck, in this paper, we propose to integrate
statistical ML models with knowledge (expressed as logical rules) as a
reasoning component using Markov logic networks (MLN, so as to further improve
the overall certified robustness. This …

end end-to-end machine machine learning reasoning robustness