In the course “Advanced Machine Learning”, the students built upon their basic statistical, mathematical and algorithmic knowledge. An informal prerequisite is the content of “Fundamentals of Machine Learning” or similar courses. Most of the topics in this lecture focus on Neural Networks. In addition to the lectures, we offer tutorial session, in which the theoretical contents will be transferred to implementations with Python using PyTorch.
After the course, the students will be able to evaluate different methods of machine learning against each other in complex use cases. They can describe and explain the differences and their advantages and disadvantages, as well as the conditions for each algorithm. Implementation competences in Python are expected after the course.
- Generative/ Discriminative Models, Regression, Features, Evaluation
- Statistical und mathematical foundation
- Neural Networks
- Convolutional Neural Networks, Recurrent Neural Networks, Generative Models, Bayesian and Gaussian Networks
- Attention Modules, Distance Metric Learning, Gradient Boosting
- End-to-end Systems, Optimization, Explainable AI