Abstract:Traditional cloud-based IoT architectures suffer from many issues, including scalability, communication and computational efficiency, in addition to privacy.This motivated the need for new emerging tr...Traditional cloud-based IoT architectures suffer from many issues, including scalability, communication and computational efficiency, in addition to privacy.This motivated the need for new emerging trends such as Edge, Fog, and Pervasive Computing, where we merge hierarchical computing with efficient communication, leveraging learning-based distributed optimization, in order to resolve many of the issues highlighted above.In this tutorial, we will highlight the motivation behind distributed AI models for Internet of Things (IoT) applications, and cyber-physical systems (CPS), in light of traditional cloud-based architectures.We will discuss state-of-the-art contributions we have recently published regarding distributed inference/classifications in IoT, and multi-drone systems, taking into consideration privacy and mobility of network users.We will motivate the need for segment-based vs layer-based inference for achieving different objectives as part of distributed inference over resourceconstrained IoT devices.Read More