Students understand basic statistical concepts relevant to machine learning.
They can formulate given problems as specific machine learning tasks and have an understanding of selected machine learning algorithms and their properties.
They are able to select suitable methods for a concrete ML task and to test their suitability.
They have basic knowledge of data pre-processing.

None

The module covers the following topics/contents:

• Basic statistical terms for machine learning
• Pre-processing and Data Preparation
• Fundamentals of AI (e.g. definitions of Machine Learning, Deep Learning, Model Life-Cycle, selected ML models)
• Neural Network fundamentals (perceptron)
• Selected applications of AI (e.g. classification, regression, object detection and recognition, segmentation)

The following literature is recommended as an example:

• T. Hastie, R.Tibshirani, J.Friedman, The Elements of Statistical Learning: Data Mining, Inference and Prediction, Springer, 2009
• V. Lakshmanan, M. Görner, R. Gillard, Practical Machine Learning for Computer Vision, O'Reilly, 2021
• A. Crane, Machine Learning with Python, Independently Published, 2020

Lecture with integrated practical exercises.
Programming exercises with Python (in groups of max. 20 students).
Individual assignments (information & submission on Moodle platform): Programming tasks, protocols, answering questions on the self-learning material provided.

Integrated module examination
Immanent examination character: Active participation in class, homework, elaborated exercises, written or oral examination.