732A82 · 6 credits · Advanced level (A1F) · Datavetenskap
Deep Learning
Active · next start VT 2027
92%
passed the latest regular sitting
DAT1 · 29 May 2026 · 24 students
77%
passed the regular sittings, all sittings over the last 5 years
DAT1 · 47 students
76%
Harder than 76% of courses at advanced level
Compared with 285 courses at the same level, ordinary exams over the last three academic years. 47 students.
Part of 1 programme
Other module
DAT1 Examination
- A
- B
- C
- D
- E
- F
Main rounds
77% passed · 47 students
- 92%24
- 61%23
Later rounds
73% passed · 15 students
- 88%8
- 57%7
- Pass a later round: 73% (15 students), compared with 77% (47 students) on the ordinary exam
- Get B or A: 35% (62 students)
Show small sittings (1)
Sittings with fewer than 5 students, often credit transfers or special sittings. They are not part of any figure on this page.
- 100%3
Other modules
Partial exams, hand-ins and labs. They are not part of the figures at the top.
Hand-in or lab
LAB2 Laboratory work
- P
Main rounds
100% passed · 47 students
- 100%29
- 100%18
Later rounds
100% passed · 5 students
- 100%5
- Pass a later round: 100% (5 students), compared with 100% (47 students) on the ordinary exam
Show small sittings (2)
Sittings with fewer than 5 students, often credit transfers or special sittings. They are not part of any figure on this page.
- 100%1
- 100%2
Other module
MUNT Oral presentation
- P
Main rounds
100% passed · 54 students
- 100%30
- 100%24
Later rounds
No sittings with at least 5 students.
About the course
Aim
After completion of the course the student should at an advanced level be able to:
- design and apply artificial neural networks to signal, image or data analysis that learn from previous experience and data
- use relevant concepts, methods, and software within Deep Learning in order to formulate, structure and solve practical problems that involve large and complex data
- motivate a deep learning architecture and hyperparameter settings that are appropriate for a given data structure, problem formulation and application area
- evaluate the performance of predictions from Deep Learning models
- argue and orally explain and discuss solutions and conclusions in dialogue with other groups
- plan and carry out tasks within given time frames
- critically reflect upon perspectives of sustainability related to Deep Learning
Content
The course deals with:
- Shallow and deep neural networks
- Regularization, drop out and early stopping. Optimization of deep neural networks
- Convolutional neural networks and image analysis
- Deep recurrent neural networks and sequence analysis
- Autoencoders and feature extraction
- Generative Adversarial neural networks
- Supervised and unsupervised Deep Learning
- Sustainability within Deep Learning
- Examiner
- Anders Eklund
- Main field of study
- Datavetenskap