Assumed prior knowledge
You must have completed the course Introduction to Deep Learning 2020-2021 or Deep Learning and Neural Networks 2019-2020 with a grade of at least 8.5 or pass an equivalent course elsewhere. See the registration procedure below.
In recent years we witness an explosion of research, development, and applications of Deep Learning. The main objective of this course is to provide a wide overview of the current state of this area and to focus on a few, carefully selected topics, covering them in depth by studying and presenting most relevant papers, and doing own research on these selected topics. This research will have a form of producing new experimental results, developing new algorithms or theories and documenting findings in scientific reports. The best reports can be submitted to conferences or published as research papers.
During the course, after a few introductory lectures, students will work (in small teams) on selected topics/problems, performing experiments on GPU-computers (if applicable), reporting on their progress during weekly meetings. Each team will have to summarize their work in a final presentation and a project report.
During the course students will:
gain an overall picture of the recent developments in Deep Learning,
identify some promising research directions
gain some hands-on research experience, including studying related papers, identifying research problems, inventing solutions of these problems, verifying these idea by experimenting and documenting findings in a scientific style,
learn to work together is small research teams,
learn to prepare and give presentations,
learn to write scientific reports.
The most recent timetable can be found at the Computer Science (MSc) student website.
Mode of instruction
Lectures, discussions, feedback on students presentations and reports.
Total hours of study: 168 hrs. (= 6 EC)
The final grade will depend on student's participation in discussions, quality of presentations, the final report. Details of will be announced at the beginning of the course.
The teacher will inform the students how the inspection of and follow-up discussion of the exams will take place.
Various articles, reports, conference proceedings.
Students should also sign up for the course via uSis before 10 January 2022. Due to the format of the course, the maximal number of students that can participate in this course is limited to 30. In case when more than 30 students would like to attend this course we will use the final grade for the required courses (see the Admission Requirements) and the result of individual interviews with course organizers to make the final selection.
Check this link for information about how to register for courses.
Lecturer: dr. Wojtek Kowalczyk
This course is also suitable/recommended to PhD students who want to use Deep Learning in their projects.