Advancements in TinyML are opening the doors to an exciting new future where IoT endpoints can store, process and manage data on the edge. This is a world where Machine Learning (ML) applications can be run on miniature devices such as microcontrollers, which are in turn used for a whole plethora of life-easing applications from predictive maintenance, building automation, the provision of audio analytics to vision and motion detection…and much more.
This training trilogy provides an overview of the benefits to be extracted from edge Machine Learning, whereby an ML algorithm can train a model, evaluate its own performance, and make predictions.
We look at the IoT edge architecture, TinyML device examples and applications where single-chip solutions that integrate Machine Learning and wireless connectivity make sense. This series culminates with a session during which you can learn how to build a complete tinyML application, end-to-end, using the latest best practices in embedded machine learning.