Advanced Deep Learning (ADL)

Course content

Deep learning has pushed the boundaries in Artificial Intelligence (AI) and has been outperforming the state-of-the-art in numerous applications across a wide range of domains. These include object classification in images, information retrieval along with web search, natural language processing tasks such as automatic translation, and bioinformatics. This course will give you detailed insight into deep learning, covering algorithms, theory and tools in this exciting field.


BSc Programme in Machine Learning and Data Science
MSc Programme in Computer Science

Learning outcome

Knowledge of

  • Convolutional neural networks

  • Recurrent neural networks

  • Generative neural networks, such as

    • Variational autoencoders

    • Generative adversarial networks (GANs)

  • Theory of deep learning

  • Topics in deep learning, exemplified by

    • Restricted Boltzmann machines

    • Fully convolutional neural networks

    • Graph neural networks

    • Deep reinforcement learning


Skills to

  • Select appropriate methodology to solve deep learning problems

  • Implement selected deep learning algorithms using state-of-the-art tools

  • Design and train deep learning algorithms


Competences to

  • Reflect upon the capabilities and limitations of deep learning algorithms

  • Recognising and describing possible applications of deep learning methodology

  • Design, optimise and use advanced deep models

  • Apply the learned methodology to applications in analysis of real-world data such as images, sounds and text

  • Analyse deep learning algorithms

The course will mix lectures, exercise classes, and project work.

See Absalon for course litterature.

Academic qualifications corresponding to the previous courses on the BSc in Machine learning & data science. As a minimum this implies:

1. Linear algebra corresponding to the course Lineær Algebra i datalogi (LinAlgDat).
2. Calculus corresponding to the courses Introduktion til matematik i naturvidenskab (MatIntroNat) and Matematisk Analyse (MatAn).
3. Basic statistics and probability theory corresponding to the course Sandsynlighedsregning og statistik (SS).
4. Machine learning corresponding to Introduktion til Machine Learning (IntroML) or Machine Learning 1 (ML1) or Machine Learning (ML). Please note that these courses include basic deep learning.
5. Programming experience in Python.

The course is equivalent to NDAB20002U Artificial Intelligence (AI). It is not allowed to pass AI and take Advanced Deep Learning (ADL)

The course is identical to the discontinued course NDAB20002U Advanced Deep Learning (ADL). Therefore you cannot register for NDAB21009U - Advanced Deep Learning (ADL), if you have already passed NDAB20002U Advanced Deep Learning (ADL).
If you are registered with examination attempts in NDAB20002U Advanced Deep Learning (ADL) without having passed the course, you have to use your last examination attempts to pass the exam in NDAB21009U - Advanced Deep Learning (ADL). You have a total of three examination attempts.

Continuous feedback during the course of the semester
7,5 ECTS
Type of assessment
Continuous assessment
Continuous assessment of 4 written assignments. All assignments must be passed. The final grade is based on an overall assessment.
All aids allowed
Marking scale
7-point grading scale
Censorship form
No external censorship
Several internal examiners
Criteria for exam assessment

According to learning outcomes.

Single subject courses (day)

  • Category
  • Hours
  • Lectures
  • 32
  • Preparation
  • 68
  • Exercises
  • 46
  • Exam
  • 60
  • English
  • 206


Course number
7,5 ECTS
Programme level

1 block

Block 4
No limit.
The number of seats may be reduced in the late registration period
Study Board of Mathematics and Computer Science
Contracting department
  • Department of Computer Science
Contracting faculty
  • Faculty of Science
Course Coordinator
  • Stefan Horst Sommer   (6-787472726a7745696e33707a336970)
Saved on the 09-12-2021

Are you BA- or KA-student?

Are you bachelor- or kandidat-student, then find the course in the course catalog for students:

Courseinformation of students