How to use AI accelerators in IoT devices

This workshop will serve as an education on how to use neural accelerators like Google Coral or whole development systems like Jetson Nano to enable the use of machine and deep learning algorithms on IoT devices.

The Internet of Things (IoT) has enabled the development of smart devices and cheap automation of simple processes in users’ homes. One of the problems of these devices is that they have weak processing power, so the processing of data from the sensors and cameras of these devices is limited. As a solution, IoT companies often use their central server/cloud to which user data from their personal IoT devices is sent and processed. With this approach, users cannot use their IoT devices in case of loss of Internet connection to the central server, and there is a risk to the security of user data. We can partially eliminate these problems if we transfer a significant amount of data processing to the user’s IoT devices themselves.