inf5450 - Current topics in applied deep learning (Complete module description)

The seminar requires attending a foundational lecture in the field of Machine Learning and Deep Learning.

Professional competence
The students

• have an overview of selected current challenges in the field of applied deep learning, along with exemplary solution approaches, and can contextualize the latter within the broader methodological context.

Methodological competence
The students

• can independently explore topics using current research literature and critically reflect upon them.

Social competence
The students

• can present solution approaches for problems in this area to the plenary and defend them in discussions.

Self-competence
The students

• are able to assess their own subject-specific and methodological competence. They take responsibility for their competence development and learning progress and reflect on these independently. In addition, they independently work on learning content and can critically reflect on the content.

This seminar provides insights into selected methodological challenges  in the field of applied deep learning. Depending on the instantiation of  the module, different emphases will be placed, such as the modeling of  long-range interactions or methods for improving the label efficiency of  machine learning algorithms, e.g. through self-supervised learning.

at the end of the lecture period/ intermediate exams

oral exam / portfolio / presentation