Book Image

TinyML Cookbook

By : Gian Marco Iodice
Book Image

TinyML Cookbook

By: Gian Marco Iodice

Overview of this book

This book explores TinyML, a fast-growing field at the unique intersection of machine learning and embedded systems to make AI ubiquitous with extremely low-powered devices such as microcontrollers. The TinyML Cookbook starts with a practical introduction to this multidisciplinary field to get you up to speed with some of the fundamentals for deploying intelligent applications on Arduino Nano 33 BLE Sense and Raspberry Pi Pico. As you progress, you’ll tackle various problems that you may encounter while prototyping microcontrollers, such as controlling the LED state with GPIO and a push-button, supplying power to microcontrollers with batteries, and more. Next, you’ll cover recipes relating to temperature, humidity, and the three “V” sensors (Voice, Vision, and Vibration) to gain the necessary skills to implement end-to-end smart applications in different scenarios. Later, you’ll learn best practices for building tiny models for memory-constrained microcontrollers. Finally, you’ll explore two of the most recent technologies, microTVM and microNPU that will help you step up your TinyML game. By the end of this book, you’ll be well-versed with best practices and machine learning frameworks to develop ML apps easily on microcontrollers and have a clear understanding of the key aspects to consider during the development phase.
Table of Contents (10 chapters)

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...