Exam
Exams would be announced on InfoStud.
Booking is mandatory (and it is normally allowed until a week before the exam).
Exam marking
The exam score would be composed of two parts, each counting equally for the final mark:
An exam on the theory (written)
A practical part, which consists of
Assignments in Python/Pytorch, communicated during the course and to be submitted by the given deadlines during the course, counting for 2/3
A final project and its presentation, counting for 1/3
For the students of Data Science, in relation to the Laboratory lectures, there would be an extra part, counting as much as each of the above 1 and 2:
Python programming laboratory assignments and homeworks
Important notes:
The assignments and the final projects (part 2) must be submitted in groups of size [3-5]. The first lectures are an opportunity to team up in person and/or via discussions on the Google group
In order to take part in 1, it's necessary to achieve a pass on part 2 of the exam
If you pass part 2, you may book the exam part 1 during the course of the next calendar year, i.e. scores in part 2 would remain valid for a calendar year
Bonus points may be given at the discretion of the lecturers.
Final Project
Each group would be assigned to deepen a specific course topic by the further reading of a relevant paper, the re-implementation and benchmarking of its algorithms, the preparation of a report and a presentation to the class. The participation in Kaggle competitions may be alternatively proposed by the students and would be agreed with the lecturer.
Ethical Code of Conduct
Plagiarism is severely prohibited and, in any form, is regarded as a serious violation of the ethical code of conduct. Plagiarism includes the submission of an assignment or project whose source code or report bears strong resemblance to another persons's source code or report, including other FDS projects and/or resources that can be found online. After submission, every project would be checked against plagiarism, including automatic detection tools. Assignments and projects resulting incurring in plagiarism would be invalidated.