Edge Computing is a pattern in which part of the computation is done on decentralized edge devices and is a great way to extend cloud computing. Using this pattern, Artificial Intelligence (AI) models are trained in the cloud and deployed on the edge which has the advantages like speed, availability and reduced need of bandwidth.

Azure IoT Edge is a fully managed service built on Azure IoT Hub.
Via Azure IoT Edge it is possible to deploy cloud workloads—artificial intelligence, Azure and third-party services, or own logic—to run on IoT devices.
Using Azure IoT Edge is possible to deploy models built and trained in the cloud and run them on-premises.
This presentation demonstrates how you can run data processing and AI related workloads on devices, including real life use-cases and useful demos.