Conclusion

This chapter provides an extensive conclusion of the research work undertaken throughout this book. It identifies its main contributions to the emerging field of embedded machine learning processors. The chapter begins with discussing the conclusions presented in the individual chapters and how they fit into the building blocks of Machine learning (ML) at the (extreme) edge. The section also presents the book’s main contributions while discussing the remaining challenges and opportunities. Subsequently, a brief overview is provided to conclude this book with a reflection and suggestions for future work to further propel the hardware development toward flexible and efficient ML computation. Finally, a brief retrospection on the role of this book in moving the field of (extreme) edge ML toward heterogeneous multi-core systems is provided.