Autoplay
Autocomplete
Previous Lesson
Complete and Continue
Edge Intelligence For Control Engineers
Introduction
Introduction (0:43)
Pre-Requisites (1:14)
Introducing Background Control System
Introduction (2:02)
Demo Factory Control System Architecture (1:33)
Introducing Demo Factory Control Hardware (2:23)
Building Control System Logic (4:21)
Demonstrating Demo Factory Control System (1:12)
Conclusion: Setting The Stage For Edge Intelligence (1:11)
Implementing Pub-Sub Communication Using MQTT
Introduction (0:58)
Publish-Subscribe Communication Fundamentals (3:26)
How MQTT Communication Protocol Works (2:26)
Implementing MQTT Pub-Sub Communication For Demo Factory (3:13)
Installing an MQTT Broker at the Edge (3:01)
Creating Demo Factory MQTT Clients (4:31)
Demonstrating MQTT Communication (3:45)
Conclusion: setting The Stage For Machine Learning Integration (1:09)
Building & Integrating ML Image Classifier Into Control System
Introduction (1:55)
Fundamentals of Convolutional Neural Networks and Tensorflow (3:36)
Introduction to Google Colab ML Development Environment (1:40)
Gathering Images and Creating Training Dataset (2:54)
Training Image Classification Model Using Python, Tensorflow and Keras API (11:13)
Saving and Testing Image Classification Model (3:58)
Introducing Tensorflow Lite: ML For Edge Devices (3:26)
Converting Image Classification Model Into Tensorflow Lite Model (6:39)
Deploying Tensor-flow Lite ML Model onto Edge Device (1:34)
Building Python App For Image Classification Using TFLite Model, raspberry Pi and Pi Camera (5:54)
Integrating Python Image Classifier with Control System Using MQTT (5:17)
Demonstrating Edge Intelligent Demo Factory (3:19)
Conclusion
Conclusion (0:48)
Teach online with
Introduction
Lesson content locked
If you're already enrolled,
you'll need to login
.
Enroll in Course to Unlock