Advanced Deep Learning for Image Processing
Course, Master's level, 1MD042
Expand the information below to show details on how to apply and entry requirements.
Spring 2026 Spring 2026, Uppsala, 33%, On-campus, English
- Location
- Uppsala
- Pace of study
- 33%
- Teaching form
- On-campus
- Instructional time
- Daytime
- Study period
- 23 March 2026–7 June 2026
- Language of instruction
- English
- Entry requirements
-
120 credits. Participation in Deep Learning and Neural Networks. Participation in on of the courses Introduction to Image Analysis and Computer-Assisted Image Analysis. Proficiency in English equivalent to the Swedish upper secondary course English 6.
- Selection
-
Higher education credits (maximum 285 credits)
- Fees
- If you are not a citizen of a European Union (EU) or European Economic Area (EEA) country, or Switzerland, you are required to pay application and tuition fees.
- First tuition fee instalment: SEK 12,083
- Total tuition fee: SEK 12,083
- Application deadline
- 15 October 2025
- Application code
- UU-61609
Admitted or on the waiting list?
- Registration period
- 9 March 2026–29 March 2026
- Information on registration from the department
Spring 2026 Spring 2026, Uppsala, 33%, On-campus, English For exchange students
- Location
- Uppsala
- Pace of study
- 33%
- Teaching form
- On-campus
- Instructional time
- Daytime
- Study period
- 23 March 2026–7 June 2026
- Language of instruction
- English
- Entry requirements
-
120 credits. Participation in Deep Learning and Neural Networks. Participation in on of the courses Introduction to Image Analysis and Computer-Assisted Image Analysis. Proficiency in English equivalent to the Swedish upper secondary course English 6.
Admitted or on the waiting list?
- Registration period
- 9 March 2026–29 March 2026
- Information on registration from the department
About the course
The course covers deep learning for visual data such as data-driven image classification, linear classification and backpropagation. It covers convolutional neural networks (CNN) and methods for training, visualising and interpreting these, generative adversarial networks (GANs), different architectures and applications within image analysis (classification, detection, segmentation). The possibilities and limitations of deep learning, in particular in image analysis, are discussed.
Reading list
No reading list found.