Areas of Competence: Knowledge and Understanding; Use, application and generation of knowledge; Communication and cooperation; Scientific self-understanding / professionalism.
The aim of the course is to provide both fundamental understanding and practical knowledge of deep learning techniques for independently applying research and development in this important and growing branch of artificial intelligence. On successful completion of this course students will have knowledge on basic neural network and deep learning concepts and their main applications, e.g. in the field of image processing.
The given theoretical foundations in deep learning will be encouraged by a strong practical focus with various appropriate examples in the lecture and laboratory. After completing the course, successful students will be able to understand and apply basic deep learning techniques to a range of practical problems, like image classification or semantic segmentation. They can (1) identify and utilize an efficient approach for a given task, (2) design and implement a practical realization, (3) test the proposed implemented system for validity and (4) they are able to provide algorithmic refinement and maintenance.
On completing the course, students should have improved presentation and team working skills due to the cooperation in small project teams on given problems. They learn to follow design requirements by understanding of written questions and describe and interpret findings in a written report using scientific language.
On completing the course, students should be able to improve their working ethics through evaluating individual efforts and strictly avoiding plagiarism.