Chapter 8: Toward the Next TinyML Generation with microNPU

Here, we are at the last stop of our journey into the world of TinyML. Although this chapter may look like the end, it is actually the beginning of something new and extraordinary for Machine Learning (ML) at the very edge. In our journey, we have learned how vital power consumption is for effective and long-lasting TinyML applications. However, computing capacity is the key to unlocking new use cases and making the "things" around us even more intelligent. For this reason, a new, advanced processor has been designed to extend the computational power and energy efficiency of ML workloads. This processor is the Micro-Neural Processing Unit (microNPU).

In this final chapter, we will discover how to run a quantized CIFAR-10 model on a virtual Arm Ethos-U55 microNPU.

We will start this chapter by learning how this processor works and installing the software dependencies to build and run the model on the Arm Corstone...