Machine Learning in Embedded Systems: Limitations, Solutions and Future Challenges
Eleftherios Batzolis, Εleni Vrochidou, George A. Papakostas
Abstract
Machine learning has attracted a lot of interest in the last few years as a solution to a variety of difficult challenges in many disciplines. An emerging area is that of embedded devices, where machine learning is deployed to efficiently carry out tasks like data analysis, prediction, and decision-making in real-time applications. Challenges such as the necessity for fast and effective algorithms and the restricted resources available in embedded systems to cover the computational and storage demands need to be confronted to successfully integrate machine learning models into embedded systems. This work aims to provide an overview of the use of machine learning in embedded systems, including past and current solutions, and to present the challenges that need to be addressed. Future directions for the use of machine learning in embedded systems are also discussed.