Machine Learning: Supervised Techniques (2VL)
||Wed 15:30-17:00, room MT 226
||Wed Oct 05, 2016
||VL, 2h, weekly
Machine learning is concerned with inferring models/relationships by learning from data. Machine learning methods are gaining importance in various fields, such as, process modeling, speech and image processing, and so forth. In recent years, bioinformatics has become one of the most prominent application areas of machine learning methods: The massive data amounts produced by recent and currently emerging high-throughput biotechnologies provide unprecedented potentials, but also pose yet unseen computational challenges in the analysis of biological data.
This course focuses on so-called supervised machine learning techniques, that is, methods aiming at models that classify data (classification) or predict continuous targets from inputs (regression). The students should acquire skills to choose, use, and adapt methods for classification, regression, and feature selection for tasks in science and engineering. The students should particularly understand the underlying mathematical objectives and principles of supervised machine learning methods. Furthermore, the students should be able to evaluate the results of supervised machine learning techniques.
- Basics of classification and regression
- Evaluation of machine learning results (confusion matrices, ROC)
- Under- and overfitting / bias and variance
- Cross-validation and hyperparameter selection
- Support vector machines and kernels
- Random forests
- Neural networks and deep networks
- Feature selection