Machine Learning from the Cloud to the IoT

Machine Learning and the IoT are a match made in heaven. After all, IoT devices collect mountains of sensor data, what better way to uncover insights and actions than through sophisticated, modern computing methods like ML and AI? 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.

    But modern embedded systems, microcontrollers and single-board computers are getting more powerful, and more sophisticated, and its becoming increasingly possible to bring Machine Learning closer to sensors and IoT devices. "Edge ML" enables quicker insights, tighter security, and even true predictive action, and it's going to become the norm in the IoT in the near future.

    In this session, we'll explore the state of the art in ML, work through the process of building and training models in the cloud, and finally, explore building IoT solutions that can run ML inferencing in real-time on low-cost devices.

    What you'll learn

    • Key differences between AI, ML and Deep Learning
    • How to build and train ML models using desktop and cloud infrastructure
    • Advantages of performing ML inferencing on the Edge
    • How to create ML models for constrained devices
    • Using purpose-built Single Board Computers (Google Coral, Nvidia Jetson) for inferencing
    • Performing ML inferencing with Microcontrollers (Particle)
    • Combining Edge inferencing with Mesh networking
    • The future of ML on the edge

    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 Particle Platform
      • 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: Exploring ML and Mesh Networking
      • Lab 2: Hacking Challenge and Free Exploration

    Computer Setup

    Brandon Satrom
    Developer Evangelist, Particle

    Brandon is the Developer Evangelist for Particle, the founder of Carrot Pants Press, a maker education and publishing company, and an avid tinkerer and maker.

    Programutvikling uses cookies to see how you use our website. We also have embeds from YouTube and Vimeo. How do you feel about that?