Uploaded August 2022 | Updated September 2026, 2 weeks ago

---

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.

00:01:37 Agenda
00:04:52 Introduction to MAB Labs
00:06:19 Machine Learning
00:06:19 Overview
00:13:40 Machine Learning in 2022
00:16:23 Machine Learning at the Edge in 2022
00:18:52 Tools & Frameworks
00:18:57 TensorFlow
00:21:31 NXP eIQ and NXP eIQ Toolkit
00:24:27 Torizon
00:31:45 Hands-On Overview
00:35:55 Workshop / Demo
01:08:35 Recap and Next Steps
01:11:48 Q&A

» Torizon: toradex.com/torizon
» Toradex System on Module (SoM): toradex.com/computer-on-modules
» iMX8 System on Module: toradex.com/computer-on-modules/apalis-arm-family/nxp-imx-8

#Torizon #NXPeIQ #Tensorflow