The explosion of efficient machine learning algorithms has enabled a multitude of solutions at the edge. Low power devices are now capable of making decisions and acting on them without any involvement from the cloud. NXP's eIQ ("edge intelligence") framework provides the key ingredients to do inference with neural network (NN) models on embedded systems and deploy ML algorithms.
In this hands-on workshop, Mohammed Billoo demonstrates how NXP's eIQ framework can be used and deployed on a system with a Toradex SoM, running Torizon. Specifically, he demonstrates how to load a model onto the system and conduct inference from a contrived dataset, using the Neural Processing Unit on the iMX8 processor.