Machine Learning from the Cloud to the IoT

The problem is, leveraging ML with IoT has historically meant backhauling all your sensor data to the Cloud. When the cloud is involved, security is a concern, and in the realm of IoT, security is often a dirty word.

In this workshop, you’ll learn how to leverage the power of Machine Learning on Edge Devices and build secure, cloud-independent IoT applications.

Day 1

Section 1: The Basics of Machine Learning

Session 1: Demystifying AI, ML, etc.

• Lab 1: Building your first ML Model
• Session 2: ML models for Complex Data: CNNs and LSTMs
• Lab 2: Building a CNN for Image Recognition

Section 2: The Basics of IoT

• Session 1: Introducing the Blues Wireless Ecosystem
• Lab 1: Claiming your first Device
• Session 2: Working with Sensors and Actuators to collect data
• Lab 2: Working with Sensor Data

Day 2

Section 3: ML and the IoT

• Session 1: Why ML and the IoT
• Session 2: ML at the Edge with Single Board Computers (SBCs)
• Lab 2: Building ML Models for Edge Inferencing
• Lab 3: Inferencing on SBCs
• Session 3: ML at the Edge with Microcontrollers (MCUs)
• Lab 4: Building ML Models for Microcontrollers
• Lab 5: Inferencing on MCUs
  

Section 4: The future of ML and the IoT

• Session 4: What's next for ML on the Edge?
• Lab 1: Hacking Challenge and Free Exploration

Computer Setup

Attendees will need to bring a laptop with the following installed:

• Visual Studio Code - https://code.visualstudio.com/download
• PlatformIO IDE extension for VS Code - https://platformio.org/
• Python 3.6 or greater - https://python.org
• Node.js - https://nodejs.org
• Edge Impulse CLI (npm install -g edge-impulse-cli)
• Chromium-based web browser (e.g. latest version of Chrome, Edge, Brave)
• Set up a free account on Blues Wireless Notehub @ notehub.io
• Set up a free account on Edge Impulse Studio @ studio.edgeimpulse.com