The students know how and when to apply supervised learning methods. Additionally, they have a comprehensive overview on supervised ML methods and the new trends developing in this field.
Further, they are able to apply the ML cycle for supervised ML techniques to complex data with the scripting languages R and Python.

Completion of the modules "Statistics", "Introduction to Machine Learning", and "Unsupervised Learning"

The module covers the following topics/contents:
Introduction to supervised ML

• What is supervised learning?
• Semi-supervised vs. supervised learning methods
• Training vs. learning data

• Classification vs. Regression
• K-nearest Neighbors
• Tree-based Learner (CART, Gradient Boosting, Random Forests)
• Kernels
• Support Vector Machine
• Naïve Bayes Classifier
• Gaussian Mixture Models
• Linear/Logistic Regression
• Ensemble methods
• New developments in the area of supervised learning methods

• Feature engineering for special application areas (Text Analysis, Computer Vision, Signal processing, ...)
• ROC, Gini-Coefficient
• Bagging and Boosting

• How to work with complex / inhomogeneous datasets
• Advanced data preparation techniques & data augmentation methods
• Dimension reduction techniques
• Handling of special kind of data (text, images, ...)

• Supervised ML methods in script languages (R/Python)
• Application of supervised ML methods to real data (model setup, evaluation & prediction)

Lecture script as provided in the course (required)
Introduction to Machine Learning with Python: A Guide for Data Scientists. Sarah Guido. O'Reilly UK Ltd, 2016.
Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques for Building Intelligent Systems. Andreas C. Müller & Sarah Guido. O'Reilly UK Ltd. 2017
Applied Supervised Learning with R. Karthik Ramasubramanian, Jojo Moolayil. Packt Pubilishing 2019.

Integrated course - teaching & discussion, guestlectures by specialists, demonstration, exercises and practical examples, home work

Immanent examination character: two courseworks (one in accordance with the module Data Engineering) and written/oral exam