Distributed machine learning for embedded devices

The goal of the master thesis is to investigate the feasibility ofhaving distributed machine learning on embedded devices and toanalyse how the architecture of such a system can look like. A systemis proposed which enables machine learning running on multipleembedded devices to communicate with an end application. Theapplication communicates with the distributed machine learning via agateway, which decouples the application. The proposed system isimplemented as a proof of concept system, which utilizes distributedmachine learning to achieve gesture recognition. The Intel Curiemodule was selected as the embedded device, as it provides a hardwareaccelerated implementation of the machine learning algorithmsK-Nearest Neighbour and Radial Basis Function. This module alsoprovides accelerometer/gyroscope sensors for collecting gesture dataas well as Bluetooth Low Energy, which enables wireless communicationwith other devices. The implemented system shows that it is feasibleto implement distributed machine learning on embedded devices if themachine learning is hardware accelerated. If a hardware acceleratorwas not used the computational load on the embedded device willincrease, which will increase the overall power consumption. For alow powered and constrained devices, hardware accelerated machinelearning is likely the best approach to implement edge intelligence