Content, progress and pedagogy of the module

Programming experience in MATLAB or Python is recommended.

Learning objectives

Knowledge

• Have knowledge about the progress and state-of-the-art of AI-based applications in energy sector
• Have knowledge about basic machine/deep learning approaches and how to apply them (supervised learning, unsupervised learning, reinforcement learning, anomaly detection)
• Have knowledge about different machine learning models and relevant variants (ANN, decision trees, SVM (Support Vector Machine), …)
• Have knowledge about typical data-driven implementation procedures including data collection and pre-processing techniques, with end-to-end toolbox creating good training data, feature extraction

Skills

• Be able to use different machine learning approaches in electrical engineering applications
• Be able to train machine learning models and prepare training data
• Be able to analyse and understand the training results
• Be able to apply cutting-edge data-driven toolboxes for field applications.

Competences

• Be able to have a data-driven thinking and know when and why using AI for energy applications
• Be able to define a machine learning problem, gather the relevant data
• Be able to implement the machine learning models and use fundamental libraries for machine learning
• Be able to understand how to process training data and analyse the obtained model output

Type of instruction

The course is taught by a mixture of lectures, exercises, and e-learning activities.

Extent and expected workload

Since it is a 5 ECTS course module, the work load is expected to be 150 hours for the student.

Exam

Exams