
Understand what to expect and learn from this Intro to Embedded Machine course.
Explore how embedded machine learning blends embedded systems, machine learning, and tiny ML to build an acoustic event detection model, from training and feature extraction to model generation and testing.
Explore Edge Impulse and its tutorials as we dive into practical embedded machine learning workflows. Follow along with one of Edge Impulse's tutorials to get hands-on.
Connect device concepts in an introduction to embedded machine learning. Learn how devices connect to embedded machine learning workflows.
Observe data by reviewing audio in the data acquisition tab, playing events, and using the visualizer to inspect labels like alarm and ambience noise with about 28 seconds of data.
Learn to generate machine learning models tailored for embedded systems, exploring methods to deploy compact, efficient models in resource-constrained environments.
Switch to classifier mode on your mobile site, grant mic permission, and test real-time audio classification by detecting baby crying amid noise; train with baby crying samples to improve accuracy.
In this course, you will learn more about the field of embedded machine learning. In recent years, technological advances in embedded systems have enabled microcontrollers to run complicated machine learning models. Embedded devices for machine learning applications can fulfill many tasks in the industry. One typical example: sensor devices that detect acoustic or optical anomalies and discrepancies and, in this way, support quality assurance in production or system condition monitoring. In addition to cameras for monitoring visual parameters and microphones for recording soundwaves, these devices also use sensors for, for instance, vibration, contact, voltage, current, speed, pressure, and temperature.
Even though there is plenty of educational content on embedded systems and machine learning individually, educational content on embedded ML has yet to catch up. This course attempts to fill that void by providing fundamentals of embedded systems, machine learning, and Tiny ML. This course will conclude with an interactive project where the learner will get to create their own specialized embedded ML project. This project will be based on acoustic event detection using a microcontroller or your own mobile device. By the end of the course, you will be able to pick your own classifications and audio and train and deploy a machine learning model yourself. This is a great way to introduce yourself to and gain valuable experience in the field of embedded machine learning.