Better AI through Logical Scaffolding

We describe the concept of logical scaffolds, which can be used to improve the quality of software that relies on AI components. We explain how some of the existing ideas on runtime monitors for perception systems can be seen as a specific instance of logical scaffolds. Furthermore, we describe how logical scaffolds may be useful for improving AI programs beyond perception systems, to include general prediction systems and agent behavior models.

[1]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[2]  Daniel Kang,et al.  Model Assertions for Debugging Machine Learning , 2018 .

[3]  Philip Koopman,et al.  Toward a Framework for Highly Automated Vehicle Safety Validation , 2018 .

[4]  Xin Zhang,et al.  End to End Learning for Self-Driving Cars , 2016, ArXiv.

[5]  Mary L. Cummings,et al.  Artificial Intelligence and the Future of Warfare , 2017 .

[6]  Houssam Abbas,et al.  Smooth operator: Control using the smooth robustness of temporal logic , 2017, 2017 IEEE Conference on Control Technology and Applications (CCTA).

[7]  Georgios Fainekos,et al.  Evaluating Perception Systems for Autonomous Vehicles Using Quality Temporal Logic , 2018, RV.

[8]  Mykel J. Kochenderfer,et al.  Policy compression for aircraft collision avoidance systems , 2016, 2016 IEEE/AIAA 35th Digital Avionics Systems Conference (DASC).

[9]  Marco Pavone,et al.  Backpropagation for Parametric STL , 2019, 2019 IEEE Intelligent Vehicles Symposium (IV).

[10]  Calin Belta,et al.  Arithmetic-Geometric Mean Robustness for Control from Signal Temporal Logic Specifications , 2019, 2019 American Control Conference (ACC).

[11]  Yang Song,et al.  Class-Balanced Loss Based on Effective Number of Samples , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Carter C. Price,et al.  Predictive Policing: The Role of Crime Forecasting in Law Enforcement Operations , 2013 .

[13]  Dejan Nickovic,et al.  Monitoring Temporal Properties of Continuous Signals , 2004, FORMATS/FTRTFT.