DM568: Deep Learning

Study Board of Science

Teaching language: Danish or English depending on the teacher, but English if international students are enrolled
EKA: N330026102
Assessment: Second examiner: None
Grading: Pass/Fail
Offered in: Odense
Offered in: Summer school (autumn)
Level: Bachelor

STADS ID (UVA): N330026101
ECTS value: 5

Date of Approval: 01-04-2020


Duration: 1 semester

Version: Archive

Comment

The course is part of 'Summer School' and is also for foreign students, held in week 32-33.
The course is co-read with DS833: Deep Learning for Data Science (5 ECTS) summer course.

Entry requirements

The course cannot be followed by students who have passed either DM863: Deep Learning (5 ECTS), DM873: Deep Learning (10 ECTS), DS809: Deep Learning (5 ECTS) or DS833..

Academic preconditions

Students taking the course are expected to:

  • To be profound programmers (python)
  • Basic understanding of linear algebra
  • Have knowledge corresponding to two years of Bachelor's studies in computer science

Course introduction

Machine learning has become a part in our everyday lifes, from simple product recommendations to personal electronic assistants to self-driving cars. Especially Deep Learning has gained a lot of interest in the media and has demonstrated impressive results. This intensive course will introduce the student to the exciting world of deep learning. We will learn about the theoretical background and concepts driving deep learning and highlight and discuss the most noteworthy applications of deep learning but also their limitations. Furthermore, all content will immediately put into practice by suitable exercises and programming tasks.

In relation to the competence profile of the degree it is the explicit focus of the course to:
  • Give knowledge and understanding of a collection of specialized models and methods developed within Computer Science based on research on highest international level, as well as of models and methods aimed at applications in other subject areas.
  • Give skills to describe, analyze and solve computational problems by using the methods learnt, to analyze pros and cons of different methods in Computer Science, as well as to develop new variants of the methods learnt where the problem at hands requires this.
  • Give the competence to plan and execute scientific projects on a high technical level.

Expected learning outcome

The 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
  • Discuss the feasibility of deep learning approaches to concrete problems
  • Describe the theoretical mathematical foundations of the field
  • Implement and apply deep learning frameworks for solving concrete problems
  • Utilize state-of-the-art deep learning frameworks for implementing deep neural networks

Content

The following main topics are contained in the course:
  • feedforward neural networks
  • recurrent neural networks
  • convolutional neural networks
  • backpropagation algorithm
  • regularization

Literature

See itslearning for syllabus lists and additional literature references.

Examination regulations

Exam element a)

Timing

July/August

Tests

Project

EKA

N330026102

Assessment

Second examiner: None

Grading

Pass/Fail

Identification

Full name and SDU username

Language

Normally, the same as teaching language

Examination aids

To be announced during the course

ECTS value

5

Additional information

Reexamination is a new assignment to be submitted in itslearning, usually in September month.

Indicative number of lessons

60 hours per semester

Teaching Method

At the faculty of science, teaching is organized after the three-phase model ie. intro, training and study phase.

  • Intro phase (lectures) - 24 hours
  • Training phase: 36 hours, including 18 hours tutorials and 18 hours laboratory
The course will consist of frontal lectures supported by a discussion session followed by an accompanying exercise or lab session. Here, the students are supposed to directly transfer their acquired knowledge into practice by solving problems of increasing difficulty.

Studyphase activities: The students are supposed to work together in small groups and review the course material and read accompanying chapters for the next day of lectures.

Teacher responsible

Name E-mail Department
Richard Röttger roettger@imada.sdu.dk Data Science

Timetable

Administrative Unit

Institut for Matematik og Datalogi (datalogi)

Team at Educational Law & Registration

NAT

Offered in

Odense

Recommended course of study

Profile Education Semester Offer period