Few-shot learning for modeling cyber physical systems in non-stationary environments

Designing Test Environments for Cyber-Physical Systems

The transformation of industrial assets into networked entities promises to increase the productivity of manufacturing processes significantly. It is a prerequisite for the close integration of these assets into production environments that increasingly rely on computerized planning, execution, and monitoring systems. The result of combining a (mechanical) asset with extensive computational cap...

Learning in Non-stationary Environments

MARTE/CCSL for Modeling Cyber-Physical Systems

Cyber Physical Systems (CPS) combine digital computational systems with surrounding physical processes. Computations are meant to control and monitor the physical environment, which in turn affects the computations. The intrinsic heterogeneity of CPS demands the integration of diverse models to cover the different aspects of systems. The UML proposes a great variety of models and is very common...

Few-shot Learning

Though deep neural networks have shown great success in the large data domain, they generally perform poorly on few-shot learning tasks, where a classifier has to quickly generalize after seeing very few examples from each class. The general belief is that gradient-based optimization in high capacity classifiers requires many iterative steps over many examples to perform well. Here, we propose ...

Distributed Machine Learning for Cyber-Physical Systems

Wireless sensor networks (WSN) are increasingly used for environmental monitoring over extended periods of time. To facilitate deployments in remote areas, sensor nodes are typically small, solar-powered devices with limited computational capabilities. Over the duration of the deployment, harsh weather conditions can lead to problems like mis-calibration or build-up of dust on sensors and solar...