Embedded Machine Learning

Unleash the Power of Embedded Machine Learning: Empowering Devices with Intelligent Insights

This exciting and fast-paced course is designed to give you practical hands-on understanding of the principles and practices involved in deploying machine learning models on resource-constrained embedded systems. Participants will explore the fundamentals of machine learning, gain insights into the unique challenges of embedded systems, and learn techniques for preprocessing, model optimization, and deployment. The course also covers integration with edge computing and the IoT, addresses security and privacy concerns. By the end of the course, participants will possess the knowledge and skills needed to implement effective embedded machine learning solutions.

Course Highlights:

• Introduction to Embedded Machine Learning
• Python and ML
• TensorFlow and ML
• Computer Vision
• Natural Language
• Training Neural Networks
• Build Models
• Deploy Models
• Security and Privacy

Course Learning Outcomes:

• Setup a Embedded ML Development Environment
• Setup and Use TensorFlow and TensorFlowLite
• Specify hardware and software requirements for Embedded Machine Learning Systems
• Apply security and privacy to embedded ML Systems
• Setup and run Python based machine learning projects
• Deploy trained models on Embedded Systems

Software: During the first lesson you'll follow the provided links to download and install the software required for the course. All the software is from free and open-source sites.

Hardware: Students are expected to have a Raspberry Pi 4 available from Raspberry Pi or any reputable electronics dealer.

Course Typically Offered: Online in Fall and Spring quarters.

Prerequisite: Some Python and C programming experience recommended.

Next Step:  Upon completion of this class, consider enrolling in other courses in the Embedded Systems Engineering certificate program.

Contact: For more information about this course, please email unexengr@ucsd.edu.