- Students gain a profound insight into the techniques, possibilities and applicability of data mining and machine learning. After successful participation they are able to identify potential fields of application of data mining methods and machine learning methods in companies to select suitable procedures and to apply them.
- Students know all steps of the data mining process to generate knowledge from data via algorithms and can apply the individual steps to larger data sets.
- Students know the different types of machine learning and are able to apply supervised and unsupervised learning methods to practical problems.
- Students understand the theoretical background of the learned methods and are able to configure them for a certain context and to adapt them if necessary.
- Introduction to Data Mining
- Overview of the data mining process
- Pre-processing (data acquisition and generation, data selection, errors in data, standardization, cleansing/filtering, dimension reduction)
- Observation problems (cluster analysis, outlier detection)
- Prediction problems (classification, association analysis, sequence pattern analysis, regression analysis)
- Introduction to Machine Learning
- Supervised and unsupervised learning with artificial neural networks (feature subset selection, multi-layer perceptron, self-organizing maps, recurrent networks, convolutional neural networks & deep learning)
- Application and implementation of selected methods using Python, Pandas, Numpy, Scikit-learn and TensorFlow