|Type||Lecture (2 SWS) + Exercise (2 SWS)|
|Audience||Master BIW, CIW, PSE, A&R and other|
Description of the main challenges that arise when dealing with large data sets and presentations of different possibilities for data management, data cleaning and outlier detection. Basic definitions in artificial intelligence and machine learning: training, validation, backpropagation, loss functions, error metrics. Description of different machine learning methods (logistic regression, clustering, neural networks, ...) and their classification into different categories such as supervised vs. unsupervised, regression vs. classification. Usage of tools to efficiently implement machine learning methods. Interpretation and analysis of the results and presentation of the potential of machine learning with examples of the chemical and biochemical engineering field.
The students can analyze the quality of data sets and perform simple operations to clean and prepare the data for the application of different machine learning techniques. The students are able to design and apply several AI techniques using efficient software tools and they are able to transfer this knowledge to solve practical problems. The students can recognize reliable results from the application of the presented machine learning techniques and critically evaluate their limitations.
|Exam||Written / Oral + Computer-based project and presentation of 10 minutes|
|Preliminaries||Basic knowledge of linear algebra. Basic programming knowledge.|
|Literature||The slides of the course and any additional materials such as literature lists and website recommendations will be published in the virtual workrooms in Moodle provided for this purpose. Details will be announced at the beginning of the course.|
Only the information found in the LSF and the most recent edition of the Modulhandbuch der Fakultät
Bio – und Chemieingenieurwesen is binding. The content on this page may not reflect the most up-to-date information.