Developing Machine Learning Applications on the Raspberry Pi Nano
In this sessionwe will introduce the Raspberry Pi Pico development boardbased on the low-costhigh-feature RP2040 microcontroller. We will explore the Pico board features and why the board is well suited for machine-learning applications. Attendees will walk away understanding the Pico board and the fundamentals of machine learning on microcontroller-based devices.
There are a wide variety of tools developers use to deploy machine-learning models to the Raspberry Pi Pico. In this sessionwe will explore the various tools embedded software developers might be interested in using. Attendees will also learn about the general machine-learning process flow and how it fits within the standard embedded software programming model.
Before a developer creates a machine-learning modelthey must first collect the data used by the model. This session will explore how to connect and collect sensor data using Edge Impulse. We'll discuss how much data to collect and the various options for doing so. Attendees will walk away understanding how to prepare their data for training and eventual deployment to the Pico.
With sensor data now collecteddevelopers will now want to use their data to train and test a machine-learning model. In this sessionwe will use the data we gathered in the previous session to train a model. Attendees will learn how to train a model and examine the training results in order to get the desired outcomes from their model.
In this sessionwe will use the model we trained in the last session and deploy it to the Raspberry Pi Pico. We'll investigate several methods to deploy the model and test how well the model works on the Raspberry Pi Pico. Attendees will see how to deploy the model and learn about the next steps for using the Raspberry Pi Pico for machine-learning applications.
Jacob Beningo is an embedded software consultant who currently works with clients in more than a dozen countries to dramatically transform their businesses by improving product quality, cost and time to market. He has published more than 300 articles on embedded software development techniques, has published several books, is a sought-after speaker and technical trainer and holds three degrees which include a Masters of Engineering from the University of Michigan.