Honey, I Shrunk the TinyML

Explore the world of TinyML in this 49-minute conference talk from MLCon (Machine Learning Conference). Learn how to train a model and convert it for use on microcontrollers, opening up new possibilities for machine learning in compact devices. Discover techniques for shrinking models through quantization and pruning, while understanding current limitations. Follow a step-by-step demonstration on creating, training, and converting a model to TinyML, and see how to integrate and run it as C++ code on a microcontroller. Gain insights into the future of miniaturized machine learning and its potential applications in various fields.

Honey, I shrunk the TinyML | Lars Gregori