Course Syllabus

The course has the following parts

Supervised Learning (Basic parameteric models for  regression and classfication, k-NN, Decision Trees, Understanding, evaluating and improving performance, Kernel methods, fundamentals about the learning problem, ...)

Statistical Methods for Learning (Bayesian Inference, Bayesian Graphical Models, Causal inference, Fusion of Models, The CRB bound,...)

Introduction to Modeling of Large-Scale Multidomain Systems (Acausal Modeling, The Modelica Language, Differential Algebraic Systems)

Identification of Dynamical Systems (Parameter Estimation in Linear Models, Models with Disturbances, Identification in closed loop, Model Reduction,...)

Tools that you will work with:

• Python-toolboxes for Learning (Scikit-Learn etc)
• Modelon Impact (Modeling and Simulation using Modelica Language)
• Matlab and the System Identification Toolbox