Discover the incredible world of tiny Machine Learning (tinyML) and create smart projects using real-world data sensors with the Arduino Nano 33 BLE Sense, Raspberry Pi Pico, and SparkFun RedBoard Artemis Nano.
TinyML Cookbook, Second Edition, will show you how to build unique end-to-end ML applications using temperature, humidity, vision, audio, and accelerometer sensors in different scenarios. These projects will equip you with the knowledge and skills to bring intelligence to microcontrollers. You'll train custom models from weather prediction to real-time speech recognition using TensorFlow and Edge Impulse. Expert tips will help you squeeze ML models into tight memory budgets and accelerate performance using CMSIS-DSP.
This improved edition includes new recipes featuring an LSTM neural network to recognize music genres and the Faster-Objects-More-Objects (FOMO) algorithm for detecting objects in a scene. Furthermore, you'll take your tinyML solutions to the next level with microTVM, microNPU, scikit-learn, and on-device learning. This book will help you stay up to date with the latest developments in the tinyML community and give you the knowledge to build unique projects with microcontrollers!
Understand the microcontroller programming fundamentals
Work with real-world sensors, such as the microphone, camera, and accelerometer
Implement an app that responds to human voice or recognizes music genres
Leverage transfer learning with FOMO and Keras
Learn best practices on how to use the CMSIS-DSP library
Create a gesture-recognition app to build a remote control
Design a CIFAR-10 model for memory-constrained microcontrollers
Train a neural network on microcontrollers
Basic familiarity with C/C++ and Python programming is a prerequisite; however, no prior knowledge of microcontrollers is necessary to get started with this book.