DM863: Deep Learning (5 ECTS)
STADS: 15020001
Level
Master's level course
Teaching period
The course is offered in the spring semester.
Teacher responsible
No responsible teachers found, contact the department if necessary
Timetable
There is no timetable available for the chosen semester.
Prerequisites:
None
Academic preconditions:
Students taking the course are expected to:
- To be profound programmers
- Basic understanding of linear algebra
Course introductionMachine learning has become a part in our everydays life, from simple product recommendations to personal electronic assistant to self-driving cars. More recently, through the advent of potent hardware and cheap computational power, “Deep Learning” has become a popular and powerful tool for learning from complex, large-scale data.
In this course, we will discuss the fundamentals of deep learning and its application to various different fields. We will learn about the power but also the limitations of these deep neural networks. At the end of the course, the students will have significant familiarity with the subject and will be able to apply the learned techniques to a broad range of different fields.
The course builds partly on the knowledge acquired in the course DM555 but can be taken by any Computer Science or Computational BioMedicine Master student.
In relation to the competence profile of the degree it is the explicit focus of the course to:
- giving the competence to plan and execute a deep learning task by means of deep neural networks.
- providing knowledge on the different types of deep learning approaches including their advantages and disadvantages.
- transfer learned methods to new fields of applications.
- challenges the student with real-life datasets and problem-solving skills
Expected learning outcomeThe learning objectives of the course is that the student demonstrates the ability to:
- Describe the principles of deep neural networks in a scientific and precise language and notation
- Analyze the various types of neural networks, the different layers and their interplay
- Describe the feasibility of deep learning approaches to concrete problems
- Understand the theoretical mathematical foundations of the field
- Apply deep learning frameworks for solving concrete problems
Subject overviewThe following main topics are contained in the course:
- feedforward neural networks
- recurrent neural networks
- convolutional neural networks
- backpropagation algorithm
- regularization
- factor analysis
LiteratureThere isn't any litterature for the course at the moment.
Website
This course uses
e-learn (blackboard).
Prerequisites for participating in the exam
- Compulsory assignments. Bestået/ikke-bestået, intern censur ved underviser. Forudsætningsprøven er en forudsætning for deltagelse i eksamenselement a).
Assessment and marking:
- Oral exam. External marking, 7-mark scale. A closer description of the exam rules will be posted under 'Course Information' on Blackboard. (5 ECTS). (15020002).
Expected working hours
The teaching method is based on three phase model.
Intro phase: 24 hours
Skills training phase: 12 hours, hereof:
- Tutorials: 12 hours
Educational activities
- Small take home exercises
- Study latest developments and approaches of deep learning by reading recent publications
Educational formThe course will consist of frontal lectures supported by discussion sessions. The students will get accompanying exercises demonstrating the collected knowledge on practical real-world problems. The student activation is completed by a mandatory project and discussions of current state-of-the-art research papers during the study phase.
Language
This course is taught in Danish or English, depending on the lecturer. However, if international students participate, the teaching language will always be English.
Course enrollment
See deadline of enrolment.
Tuition fees for single courses
See fees for single courses.