Learning-from-signals on edge devices

Machine learning tools are being developed that support increasingly complex learning-fromsignals on "edge" devices to meet the challenges of decentralized decision making. Edge devices in this context include any electronically enabled device that can sense, process and make decisions based on locally integrated information. Component systems that use algorithms and other technologies are required to provide sensing, signal processing, learning (model selection) and classification functions for edge devices. This article focuses on the algorithms and technologies for the component systems. It includes an introductory description of the architectures that enable these functions to be ported to edge devices which have limited resources so they can execute some machine learning processes.