Skip to content


Advanced deep learning 7.5 credits

Avancerad djupinlärning
Second cycle, D7047E
Course syllabus valid: Spring 2022 Sp 3 - Present
The version indicates the term and period for which this course syllabus is valid. The most recent version of the course syllabus is shown first.

Education level
Second cycle
Grade scale
G U 3 4 5
Computer Science
Subject group (SCB)
Computer Technology
Main field of study
Computer Science and Engineering

Entry requirements

Bachelor's degree of at least 180 credits in a relevant area such as Computer Science, Engineering Physics, Electrical Engineering, Information Systems, Systems Science, or a closely related area. The studies shall have included Introductory Programming (for example D0009E Intruoduction to Programming or D0007N Objectoriented programming) and a fundamental Machine Learning course such as D7046E Neural networks and learning machines, or equivalent. Knowledge in English equivalent to English 6.

More information about English language requirements


The selection is based on 20-285 credits

Course Aim

The objective of the course is for the student to expand their knowledge and skills in Deep Learning. After passing the course, the student should be able to:

[1].   Explain and use the advanced deep learning concepts & techniques  

[2].  Describe how those advanced techniques work

[3].  Explain how the advanced techniques are, or should be, used in organizations

[4].  Evaluate results of applying the advanced analytics techniques

[5].  Analyze and reflect on the relationship between the techniques, the dataset, the problem or opportunity in hand, and the tools and technology used


The course is an advanced course in deep learning. The course is set out to provide knowledge to the students which is expected to help them address various machine learning problems with most recent state-of-the-art methodology. While specific topics will be updated based on the current development in the research area of Deep Learning, the following topics will be covered: Vanishing Gradient problem and solutions: ResNet and LSTM; reinforcement learning and artificial curiosity; Image Captioning and Question Answering; Deep Learning for NLP; Bleeding-edge architectures.

Each course occasion´s language and form is stated and appear on the course page on Luleå University of Technology's website.

Lectures, labs, assignments, case studies and project work. During the course, the students work in small groups. Some assignments or case studies in the course might contain work in contact with or about the industry. The student uses different methods and techniques, and it is important to choose the right method, technique or computer support for each task. Before and after the tasks are solved, there are lectures to present and discuss different solutions. 

Teaching is in English and on the Internet for distance students or on campus for students living here.  IT support: Learning management system (Canvas), e-mail and phone. The learning management system is used for delivering course material, information and submissions. Knowledge is shared and created within the course through virtual meetings with teachers and other students for discussions, supervision, teamwork and seminars. For students on campus, there will be meetings on campus.

If there is a decision on special educational support, in accordance with the Guideline Student's rights and obligations at Luleå University of Technology, an adapted or alternative form of examination can be provided.

Through written tests, individual and group/project assignment, different student abilities are examined. Those are: the ability to explain and use advanced deep learning techniques and the ability to solve advanced machine learning problems using deep learning (if applicable in combination with other machine learning techniques) individually and in groups.


Technical Requirements: Access to PC with Windows XP, microphone, Web cam, and permission to install software. Internet connection (minimum 0,5 Mbps).

Marcus Liwicki

Literature. Valid from Spring 2020 Sp 3 (May change until 10 weeks before course start)
Deep Learning; Ian Goodfellow Yoshua Bengio and Aaron Courville, MIT Press, 2016
Deep learning in neural networks: An overview, Jürgen Schmidhuber, Neural Networks; Volume 61, January 2015
Deep Learning Tutorial:

Search books in the library »

Course offered by
Department of Computer Science, Electrical and Space Engineering

CodeDescriptionGrade scaleCrStatusFrom periodTitle
0001Written exam/Individual examG U 3 4 54.00MandatoryS20
0002Individual tasksG U 3 4 51.50MandatoryS20
0003Group/Project workU G#2.00MandatoryS20

Study guidance
Study guidance for the course is to be found in our learning platform Canvas before the course starts. Students applying for single subject courses get more information in the Welcome letter. You will find the learning platform via My LTU.

Syllabus established
by Jonny Johansson, HUL SRT 15 Feb 2019

Last revised
by Jonny Johansson, HUL SRT 16 Feb 2021