Knowledge distillation between machine learning models has opened many new avenues for parameter count reduction, performance improvements, or amortizing training time when changing architectures the teacher and student network. In case of reinforcement learning, this technique also been applied to distill policies students. Until now, policy required access a simulator real world trajectories....

A long landing is one type of flight incident that will multiply the risk of a runway excursion. It occurs frequently but receives little attention in research due to difficulty in obtaining the real flight data. The aim of this paper is to discover key flight parameter features of long landing incidents by analyzing Quick Access Recorder (QAR) data and put forward prevention measures from the ...

Computer simulators are widely used for the study of complex systems. In many applications, there multiple available with different scientific interpretations underlying mechanism, and goal is to identify an optimal simulator based on observed physical experiments. To achieve goal, we propose a selection criterion leave-one-out cross-validation. This consists goodness-of-fit measure generalized...