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)

Designing and training a NN model

In this recipe, we will be leveraging the following NN architecture to recognize our words:

Figure 4.20 – NN architecture

The model has two two-dimensional (2D) convolution layers, one dropout layer, and one fully connected layer, followed by a softmax activation.

The network's input is the MFCC feature extracted from the 1-s audio sample.

Getting ready

To get ready for this recipe, we just need to know how to design and train a NN in Edge Impulse.

Depending on the learning block chosen, Edge Impulse exploits different underlying ML frameworks for training. For a classification learning block, the framework uses TensorFlow with Keras. The model design can be performed in two ways:

  • Visual mode (simple mode): This is the quickest way and through the user interface (UI). Edge Impulse provides some basic NN building blocks and architecture presets, which are beneficial if you have just started experimenting...