About

This course provides students with the fundamentals of edge AI and hands-on experience in designing end-to-end AI systems for resource-constrained computing devices, such as microcontrollers It aims to equip students with knowledge of hardware systems and AI model optimization techniques and tools for IoT edge devices. After completing the course, students will have the skills to implement AI models, such as computer vision, on embedded/edge devices for various real-world applications, including smart cities, sustainability, healthcare, and agriculture. The topics to be covered in this course include:

  • Introduction to Edge AI
  • ML/AI Algorithms and Computer Vision Fundamentals
  • Edge AI Hardware and Accelerators
  • Edge AI Software Frameworks and Libraries
  • Model Optimization and Pruning Techniques and Tools
  • Deployment of Edge AI Systems and Case Studies

Prerequisites

Proficiency in Python programming is essential, while C programming and a basic understanding of AI/ML, microcontrollers, and IoT systems would be a plus.

Grading

  • 3 programming assignments (45%)
  • 3 quizzes (15%)
  • Course project (40%)

Text books and references

Textbooks/References

  • TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers (2020) by Pete Warden and Daniel Situnayake TinyML Cookbook (2022) by Gian Marco Iodice
  • AI at the Edge: Solving Real-World Problems with Embedded Machine Learning (2022) by Daniel Situnayake and Jenny Plunkett.
  • Deep Learning on Microcontrollers: Learn how to develop embedded AI applications using TinyML (2023) by Atul Krishna Gupta and Dr. Siva Prasad Nandyala
  • TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers (2020) by Pete Warden and Daniel Situnayake
  • Hands-on TinyML: Harness the power of Machine Learning on the edge devices (2023) by Rohan Banerjee
  • Dive Into Deep Learning (2023), Aston Zhang, Mu Li, Alexander J. Smola, Zachary Lipton.

Similar courses:

  1. NVIDIA - Edge AI and Robotics Teaching Kit
  2. Intel - AI on the Edge with Computer Vision
  3. TinyML and Efficient Deep Learning Computing (MIT)
  4. ESE3600: Tiny Machine Learning (UPenn)
  5. edX tinyML Specialization (Harvard University)