Recommended prerequisite for participation in the module

The module builds on basic knowledge in probability and statistics theory, linear algebra and machine learning

Content, progress and pedagogy of the module

This course introduces deep learning both by presenting valuable methods and by addressing specific applications. This course covers both theory and practices for deep learning. The students will also have hands-on exercises experimenting with a variety of deep learning architectures for applications.

Learning objectives

Knowledge

Students must have knowledge about:

• models and representation learning
• Advanced topics including attention and transformer networks, autoencoders, generative adversarial networks, adversarial attacks, self-supervised learning, and deep reinforcement learning
• Regularization, optimization, hyperparameter tuning, and data augmentation
• Bias, fairness, and explainable AI
• Design and implementation of deep learning for selected applications

Skills

• Must be able to apply the taught methods to solve real-world problems.
• Must be able to evaluate and compare the methods within a specific application problem.

Competences

• Must have competences in analyzing a given problem and identifying appropriate deep learning methods to the problem.
• Must have competences in understanding the strengths and weaknesses of the methods.

Type of instruction

As descript in §17

Exam

Prerequisite for enrollment for the exam

• Submission of mini-project report

Exams

Name of exam	Deep Learning
Type of exam	Written or oral exam
ECTS	5
Assessment	7-point grading scale
Type of grading	Internal examination
Criteria of assessment	The criteria of assessment are stated in the Examination Policies and Procedures