Machine Learning Classifiers for Emergent Behavior in Complex Systems and System-of-Systems

With increasing system complexity, achieving confidence in systems becomes difficult. With the recent trend towards significant footprint of complex system’s functionality being governed by machine learning based models and algorithms, there is a need to ensure that emergent behavior associated with such systems are well analyzed and understood. This presentation discusses an approach that involves developing machine learning classifier models that learns on potential negative and positive emergent behaviors. The machine learning model observes and learns the nature of emergent behavior. The approach is illustrated through two examples – one at system level for pitch control of an aircraft, and another at system-of-system level for a swarm of UAVs.