Content, progress and pedagogy of the module

Disclaimer. This is an English translation of the module. In case of discrepancy between the translation and the Danish version, the Danish version of the module is valid.

Learning objectives

Knowledge

After having completed the module the student will have gained knowledge about selected topics within advanced machine learning. The list of topics may include, but is not limited to, the topics below. The specific curriculum will cover three to five topics. The students will be informed about the specific topics by the beginning of the course:

• Deep neural networks, including convolutional networks and recurrent networks 

• Support vector machines and kernels 

• Gaussian processes 

• Inference methods for probabilistic models, including variational inference and Markov chain Monte Carlo (MCMC). 

• Latent variable models, including topic models

Skills

After having completed the module, the student should be able to 

• explain and discuss the principles behind the machine learning models and algorithms presented in the course. 

• explain and reason about key advanced machine learning topics using correct terminology and notation from the research field. 

• apply and evaluate advanced machine learning algorithms and models for a particular problem.

Competences

After having completed the module, the student should be able to 

• analyze and evaluate the use of advanced machine learning techniques for solving a particular machine learning problem. 

• evaluate and select an appropriate machine learning algorithm for a particular problem. 

• relate and combine relevant topics from the course for solving a particular machine learning problem.

Exam

Exams