Tiny Machine Learning
This course provides both theoretical foundations and hands-on experience in machine learning for small, resource-constrained devices.
Students will first study the fundamentals of tiny machine learning algorithms before applying their knowledge in a collaborative group project, solving real-world challenges.
This course is structured into two primary parts:
In the initial phase, students will focus on the theoretical and practical aspects of tiny machine learning. Topics include:
- Fundamentals of tiny machine learning algorithms designed for resource-constrained devices.
- Theoretical principles underpinning algorithm design and optimization.
- Hands-on assignments to reinforce and apply these concepts in practical scenarios.
The second phase centers on a collaborative group project where students will tackle a current and relevant problem in machine learning for small devices. In this component, students will:
- Leverage the knowledge and skills acquired from previous courses.
- Conduct comprehensive literature reviews to identify innovative approaches.
- Collaborate in teams to develop and implement a solution addressing real-world challenges.
This two-part approach ensures that students build a strong theoretical foundation while also gaining practical, hands-on experience through collaborative problem-solving.
At the beginning of the course, the examiner provides a detailed course description that outlines the content to be covered.
Teaching Format
The teaching consists of lectures/lessons, laboratory work, project work, seminars, mandatory oral presentation and written report.
The language of instruction is English.
Assessment
The course is examined through assignments and project work.
