After successful completion of the course, students are able to...
- Understand a very broad collection of machine learning algorithms and problems
- determine when machine learning is feasible and can be meaningfully applied to specific challenges
- apply machine learning algorithms in their interested problems
- be qualified in doing researching in machine.
The lecture imparts understanding of methods from pattern classification and machine learning. The following topics are included: applications of machine learning, density estimation, regression techniques, pattern classifiers, probabilistic methods for classification, dimensionality reduction techniques, feature selection, statistical clustering, unsupervised learning, expectation-maximization algorithm, Validation, Markov process, hidden Markov models, Gaussian Processes, dynamic programming, reinforcement learning, neural networks.
The contents of this lecture are presented with slides and on the blackboard. Exercises and tutorial courses, repeated calculations and problem solving will help develop deeper understanding for the matter. There is the possibility to gain practical experience through programming assignments.
The evaluation will be based on a final (written) exam and programming assignment. The exam includes questions about theory, calculations, and practices, which covers the contents from lectures and exercise sessions.
Not necessary
Basics of Linear Algebra, Probability and Statistics, Python programming
