Print as pdf if you want a pdf! If you want a nicer printout, click off the browser's automatically added header and footer.

Blekinge Institute of Technology
Department of Mathematics and Natural Science

Revision: 1
Reg.no: BTH-4.1.14-0509-2025


Course syllabus

Deep Learning

Deep Learning

6 credits (6 högskolepoäng)

Course code: ET2638
Main field of study: Electrical Engineering
Disciplinary domain: Technology
Education level: Second-cycle
Specialization: A1N - Second cycle, has only first-cycle course/s as entry requirements

Language of instruction: English
Applies from: 2025-05-21
Approved: 2025-05-21

1. Descision

This course is established by Dean 2024-10-08. The course syllabus is approved by Head of Department of Mathematics and Natural Science 2025-05-21 and applies from 2025-05-21.

2. Entry requirements

Admission to the course requires taken courses in Signals and Systems, 5 credits, and Machine Learning or Applied Machine Learning, 5 credits. English 6.

3. Objective and content

3.1 Objective

Deep learning methods are widely applied across various fields in engineering, such as computer vision, signal processing, and remote sensing. The purpose of the course is to introduce students to neural networks and deep learning fundamentals for various applications such as classification, detection, and signal reconstruction. In addition, this course discusses various architectures such as Convolutional Neural Networks (CNNS), Recurrent Neural Networks (RNNS), and Autoencoders.

3.2 Content

  • Introduction to Artificial Neural Networks
  • Activation functions, loss functions, regularization techniques, optimization algorithms, and data preprocessing
  • Fundamentals of deep learning and deep neural networks
  • Convolutional Neural Networks (CNNs)
  • Recurrent Neural Networks (RNNs) and sequence modeling
  • Autoencoders: encoding-decoding structures, denoising, and variational autoencoders
  • Advanced deep learning methods for classification and detection
  • Training strategies: transfer learning, fine-tuning, and data augmentation
  • Applications of deep learning in various domains, including signal processing, computer vision, and time-series analysis

4. Learning outcomes

The following learning outcomes are examined in the course:

4.1. Knowledge and understanding

On completion of the course, the student will be able to:

  • Explain fundamentals of neural networks and deep learning.
  • Explain real-world applications of deep learning methods.
  • Demonstrate knowledge of the design and functionalities of deep learning methods.

4.2. Competence and skills

On completion of the course, the student will be able to:

  • Design, implement and apply deep learning methods for relevant applications,
  • Prepare datasets, propose deep learning methods and evaluate performances.
  • Implement deep learning methods for various applications using a programming language.

4.3. Judgement and approach

On completion of the course, the student will be able to:

  • Evaluate deep learning proposals and their suitability for different problems.
  • Provide a systematic approach to implement deep learning methods.

5. Learning activities

The course is conducted through lectures, exercises, projects, and assignments. A web-based course platform is used to provide students with access to course materials.

6. Assessment and grading

Modes of examinations of the course

Code Module Credit Grade
2605 On-campus Examination[1] 3 credits AF
2615 Written Assignment 3 credits GU

[1] Determines the final grade for the course, which will only be issued when all components have been approved.

The course will be graded A Excellent, B Very good, C Good, D Satisfactory, E Sufficient, Fx Failed result, a little more work required, F Fail.

The examiner may carry out oral follow-up of written examinations.

The information before the start of the course states the assessment criteria and make explicit in which modes of examination that the learning outcomes are assessed.

An examiner can, after consulting the Disability Advisor at BTH, decide on a customized examination form for a student with a long-term disability to be provided with an examination equivalent to one given to a student who is not disabled.

7. Course evaluation

The course evaluation should be carried out in line with BTH:s course evaluation template and process.

8. Restrictions regarding degree

The course can form part of a degree but not together with another course the content of which completely or partly corresponds with the contents of this course.

9. Course literature and other materials of instruction

Parts of the following books are included in the course:

Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville, MIT Press, 2016. ISBN:9780262035613
Deep Learning with Python by François Chollet, Manning Publications, 2022. ISBN: 9781617296864
Introduction to Machine Learning by Ethem Alpaydin, MIT Press, 2020. ISBN: 9780262043793

And materials from the department.