Course Schedule

Week 1 (Jan 7 & 9)

  • Lecture 1: Introduction (slides)
    • Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing (pdf)
  • Lab 1: Introduction to Tiny Machine Learning Kit (slides)

Week 2 (Jan 14 & 16)

  • Lecture 2: Introduction to Internet of Things (IoT) and Edge Analytics (slides)
  • Lab 2: MicroPython Programming for Arduino (slides)
    • MicroPython for Arduino (Link)
    • MicroPython 101 course (Link)
    • Arduino Lab for MicroPython (Link))
    • MicroPython examples for Nano BLE Sense (Link)
    • MicroPython libraries (Link)

Week 3 (Jan 21 & 23)

  • Lecture 3: IoT Devices and Embedded Systems (slides)
  • Lab 3: MicroPython and OpenMV (slides)
    • OpenMV Firmware & IDE (Link)
    • OpenMV MicroPython libraries (Link)

Week 4 (Jan 28 & 30)

  • Lecture 4: Embedded ML and Challenges (slides)
    • 2 ML Systems from the book Machine Learning Systems (Link)
  • Lab 4: Sensor Data Collection (IMU) (slides)

Week 5 (Feb 4 & 6)

  • Lecture 5: Introduction to AI and ML (slides)
    • Chapter 1: Introduction from the book Machine Learning Systems (Link)
    • Decision trees - A friendly introduction by Luis Serrano (Link)
  • Lab 5: Implementing Decision Trees for Activity Detection (slides)

Week 6 (Feb 11 & 13)

  • Lecture 6: Artificial Neural Networks (slides)
    • Chapter 3: DL Primer from the book Machine Learning Systems (Link)
    • Chapters 3-5 from the Book Dive into Deep Learning (Link)
  • Lab 6: Deploying Decision Tree for Real-Time Activity Detection (slides) -

Week 7 (Feb 18 & 20)

  • Lab 7: EdgeImpulse (slides)
  • Lab 8: Implementation of Neural Networks (ANN and CNN) (slides)

Week 8 (Feb 25 & 27)

  • Lecture 7: Convolutional Neural Networks and Computer Vision (slides)
    • Chapter 4: DNN Architectures from the book Machine Learning Systems (Link)
    • Chapters 7-8 from the Book Dive into Deep Learning (Link)
  • Lecture 8: Model Optimization and Efficiency Metrics (slides)
    • Chapter 9: Efficient AI from the book Machine Learning Systems (Link

Week 9 (Mar 4 & 6)

  • Lecture 10: Introduction to Quantization (slides)
  • Chaper 10: Model Optimizations from the book Machine Learning Systems (Link
  • Lab 9: Model Parameters and Efficiency Metrics of ANN and CNN Models (slides)

Week 10 (Mar 11 & 13)

  • Lecture 10: Advanced Quantization (slides)
    • Chaper 10: Model Optimizations from the book Machine Learning Systems (Link
  • Lab 10: Quantization (slides)

Week 11 (Mar 18 & 20)

  • Lecture 11: Pruning (slides)
    • Chaper 10: Model Optimizations from the book Machine Learning Systems (Link
  • Lab 11: Prunig (slides) —