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: 2
Reg.no: BTH-4.1.14-0071-2021


Course syllabus

Introduction to Machine Learning and Artificial Intelligence

Introduction to Machine Learning and Artificial Intelligence

7.5 credits (7,5 högskolepoäng)

Course code: ET1550
Main field of study: Electrical Engineering
Disciplinary domain: Technology
Education level: First-cycle
Specialization: G1F - First cycle, has less than 60 credits in first-cycle course/s as entry requirements

Language of instruction: Teaching is given in English
Applies from: 2021-06-07
Approved: 2021-02-18

1. Descision

This course is established by Dean 2020-10-14. The course syllabus is approved by Head of Department of Mathematics and Natural Science 2021-02-18 and applies from 2021-06-07.

2. Entry requirements

Admission to the course requires completed courses Linear algebra 6 credits, Calculus 10 credits, Programming 6 credits and taken course Statistics 6 credits.

3. Objective and content

3.1 Objective

This course aims to provide an overall understanding of machine learning techniques and their applications. The course gives the participants the opportunity to understand the concepts behind the emerging technologies and the importance of artificial intelligence, machine learning and data analytics. In addition, the course focuses on deep learning algorithms and its impact on the industry as well as the daily life and describes the future opportunities regarding intelligent and sustainable products. Furthermore, the purpose is also to gain an understanding of data preparation, different methods for machine learning, different types of machine learning problems and choice of algorithms from an application perspective.

3.2 Content

  • Introduction to Artificial Intelligence and machine learning applications
  • Data preparation (e.g. training set, validation set, test set)
  • Supervised and unsupervised approaches
  • Machine learning problems (e.g. regression, classification, clustering)
  • Machine learning algorithms (e.g. linear regression, neural networks, K-nearest neighbours, K-means)
  • Deep learning and applications (e.g. automation, perceptual task)

4. Learning outcomes

The following learning outcomes are examined in the course:

4.1. Knowledge and understanding

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

  • display basic knowledge regarding theories and methods related to machine learning approaches.
  • demonstrate knowledge regarding machine learning algorithms suitable for different problems.

4.2. Competence and skills

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

  • complete a number of assignments and perform data preparation, model selection, training and evaluation of the outcome.

4.3. Judgement and approach

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

  • identify their need for additional knowledge and independently develop their competence in machine learning field.
  • judge suitability of a machine learning algorithm for a given problem.
  • understand the limitations and applications of machine learning algorithms.

5. Learning activities

Teaching is conducted through lectures, exercises, project work and virtual study visits.

6. Assessment and grading

Modes of examinations of the course

Code Module Credit Grade
2105 Project assignment 1 2.5 credits GU
2115 Project assignment 2 2.5 credits GU
2125 Project assignment 3 2.5 credits GU

The course will be graded G Pass, UX Failed result, a little more work required, U Fail.

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

Provided by the course coordinator during the course. The material can be in both Swedish and English.

Reference literature

  • Alpaydin, E. Introduction to Machine Learning ISBN: 9780262028189, (2014) MIT Press
  • Goodfellow, I., Bengio, Y. and Courville, A. Deep Learning ISBN: 9780262035613, (2016) MIT Press
  • Chollet, F. Deep Learning with Python ISBN: 9781617294433, (2018 ) Manning Publications
  • Nielsen M. Neural Networks and Deep Learning Online book: http://neuralnetworksanddeeplearning.com/

This is not a legal document. If you would like a copy of the legal decision regarding this course plan, contact the registrar at Blekinge Institute of Technology.