Entry requirements

120 credits whereof 90 credits in science/engineering including 5 credits in programming with python or C. Participation in Computer Networks or Internet of Things or in Distributed Information Systems or Digital Communication. Participation in Probability and Statistics or Statistics for Engineers. Participation in Natural Computation Methods for Machine Learning or Statistical Machine Learning or Artificial Intelligence for Industrial Analytics. Proficiency in English equivalent to the Swedish upper secondary course English 6.

Learning outcomes

On completion of the course, the student should be able to:

• explain performance metrics and algorithms for Machine Learning for resource-constrained devices,
• identify and analyze the opportunities and trade-offs of Machine Learning for resource-constrained Internet of Things (IoT) devices,
• suggest and critically analyze solution designs for typical Machine Learning for the IoT,
• design and implement Machine Learning solutions for resource-constrained IoT devices and networks in laboratory work.

Content

Introduction including resource-efficient machine learning algorithms, hardware and architectures. Approaches for machine learning on resource-constrained IoT devices including quantization and pruning. Distributed learning for IoT devices and networks through learning at the edge, distributed and federated learning. Machine learning and data engineering for handling application data from IoT networks. Optimization of IoT networks at different protocol layers. Machine learning for IoT security and privacy. Implementation and evaluation of machine learning algorithms for IoT (labs).

Instruction

Lectures and laboratory work.

Assessment

Written exam (3 credits). Laboratory work (2 credits).

If there are special reasons for doing so, the examiner may make exceptions from the specified examination method of assessment and allow a student to be assessed by another method. An example of special reasons might be a certificate regarding special pedagogical support from the disability coordinator of the university.