PDF for print
Find calendar
| Title |
Elective course: Deep Learning
|
| Semester |
E2025
|
| Master programme in |
Computer Science
|
| Type of activity |
Course |
| Mandatory or elective |
Elective |
| Teaching language |
English
|
| Study regulation |
You register for activities through stads selvbetjening during the announced registration period, which you can see on the Study administration homepage. When registering for courses, please be aware of the potential conflicts and overlaps between course and exam time and dates. The planning of course activities at Roskilde University is based on the recommended study programmes, which should not overlap. However, if you choose optional courses and/or study plans that goes beyond the recommended study programmes, an overlap of lectures or exam dates may occur depending on which courses you choose. |
| REGISTRATION AND STUDY ADMINISTRATIVE | |
| Registration |
Read about the Master Programme and find the Study Regulations at ruc.dk |
| Number of participants |
|
| ECTS |
5
|
| Responsible for the activity |
Henning Christiansen (henning@ruc.dk)
|
| Head of study |
Henrik Bulskov (bulskov@ruc.dk)
|
| Teachers |
|
| Study administration |
IMT Registration & Exams (imt-exams@ruc.dk)
|
| Exam code(s) |
U60598
|
| ACADEMIC CONTENT | |
| Overall objective |
The purpose of elective courses is to give the student opportunitities to specialize within a specific subject area, where the student acquires knowledge, skills and competences in order to translate theories, methods and solutions ideas into their own practice. |
| Detailed description of content |
The course recaps fundamental concepts of Machine Learning and Artificial Neural Networks. The course includes:
A substantial part of the course consists of students working in groups on a selected topic, involving setting up, training, testing and experimenting with deep neural network models, as a basis for the written product. Software tools: Python, TensorFlow, Keras (some familiarity with Python is an advantage). |
| Course material and Reading list |
François Chollet: Deep learning with Python, Third Edition. Manning, 2025. Course notes and scientific papers made available on moodle. |
| Overall plan and expected work effort |
The course's 5 ECTS correspond to a total of 135 hours workload with:
|
| Format |
|
| Evaluation and feedback |
Evaluation form to be filled out (anonymously) plus open discussion on the last course day. |
| Programme |
|
| ASSESSMENT | |
| Overall learning outcomes |
After completing this course, students will be able to:
|
| Prerequisites |
|
| Form of examination |
Individual oral exam based on a written product
The character limit of the written product is maximum48,000 characters, including spaces. The character limits include the cover, table of contents, bibliography, figures and other illustrations, but exclude any appendices. Time allowed for exam including time used for assessment: 20 minutes. The assessment is an overall assessment of the written product(s) and the subsequent oral examination. Permitted support and preparation materials for the oral exam: All. Assessment: 7-point grading scale Moderation: Internal co-assessor. |
| Form of Re-examination |
Samme som ordinær eksamen / same form as ordinary exam
|
| Type of examination in special cases |
|
| Examination and assessment criteria (implemented) |
Examination and assessment criteria The assessment is based the quality of the written product and the extent to which the student can:
The use of generative AI aids in exams In this course, generative AI aids (GAI) are permitted in the work with the exam if the use is declared. You must clearly declare how you have used generative artificial intelligence (GAI). This can be included as part of a methodology section or as a short statement at the end of your exam paper. This means that you must describe how you have used GAI, e.g. for the preparatory work on the assignment, to ask questions and search for information, to receive feedback and criticism on your text, to carry out proofreading or to improve language and readability. It is important that you actively relate to your choice of tools in this way, as it is part of the entire process of creating the assignment, and thus part of your scientific method and professional communication. The use of any specific text that is GAI-generated requires citation, just as when using all other sources from which direct quotations are used. In the library's guide, you can see more about how to cite AI and how you can account for your use of GAI. However, ordinary spell checking and other language suggestions, such as those known from Word or other word processing programs, as well as programs for writing minutes and transcription, are permitted to be used in all written exams and do not need to be declared. The use of generative artificial intelligence (GAI) must always take place within the framework of Roskilde University's ‘Guidelines for using generative artificial intelligence in written exams.’ Read the guidelines here. |
| Exam code(s) | |
| Last changed | 09/09/2025 |
Find calendar (1)
PDF for print (1)