• CD102A Object-Oriented Programming (7.5 credits)
• CD120A Algorithms and Data Structures (7.5 credits)
• CM152A Mathematical Statistics for Data Science (7.5 credits)
• 7.5 credits from the course CD631E Artificial Intelligence for Data Science (15 credits)

The course is part of the degree requirements for a Master of Science in Engineering in Computer Science and Engineering (specialisation Applied Data Science)

The aim of the course is for the student to acquire in-depth knowledge and understanding of advanced aspects of machine learning and familiarise themselves with the current research front.

The course contains the following elements:

• Data transformation, Data Augmentation, adjustment/calibration of model parameters (including Advanced Feature Extraction, Hyper-parameter Optimisation)
• Interactive machine learning methods (including Human-Machine Collaboration, Active Learning, Online learning, Incremental Learning, Learning from Data Streams)
• Meta-learning algorithms and Ensemble Methods
• Advanced algorithms for supervised learning and unsupervised learning (with emphasis on discriminative and generative Deep Learning architectures)
• Reinforcement learning (including Policy Search, Policy Iteration, Value Iteration, Q-learning)

Trends and current front line research in machine learning

Knowledge and understanding

Upon completion of the course, the student shall be able to:

1. explain advanced machine learning methods and how they are used in practice.

Competence and skills

Upon completion of the course, the student shall be able to:

2. implement advanced machine learning algorithms, both individually and in groups,

3. assimilate and use published research results in machine learning, e.g. to create predictive models,

4. explore recent developments in commercial machine learning applications,

5. evaluate and compare the suitability of different methods for addressing a given problem, and

6. interpret the relevance of machine learning results.

Judgement and approach

Upon completion of the course, the student shall be able to:

7. analyse and evaluate academic publications in machine learning, and

8. critically analyse the strengths and weaknesses of scientific arguments for both theoretical and experimental results.

Lectures, data laboratories, seminars, project work and self-study.

The following are required to pass the course

• passing grade on report in group project (7 credits, Pass/Fail) (Intended learning outcomes 2–5, 7)
• passing grades on lab session assignments (3 credits, Pass/Fail) (Intended learning outcomes 2, 5, 6)
• passing grade on written examination (5 credits, UA) (Intended learning outcomes 1, 8)

For all assessments, the materials must be presented in a manner that makes it possible to discern individual performance.

The final grade corresponds to the grade of the written examination.

• Aurlien G. (2017). Hands-On Machine Learning with Scikit-Learn and Tensorflow: Concepts, Tools, and Techniques to Build Intelligent Systems. O'Reilly Media.
• Goodfellow, I., Bengio, Y. & Courville, A. (2016). Deep Learning. The MIT Press.
• Han, J., Kamber, M., & Pei, J. (2022). Data mining: Concepts and techniques (4th edition). Morgan Kaufmann.
• Russell, S. J. & Norvig, P. (2020). Artificial intelligence: a modern approach. (4th edition), Pearson Education.
• Witten, I. H., Frank, E. & Hall, M. A. (2016). Data mining: practical machine learning tools and techniques (4th edition), Morgan Kaufmann.

In addition to the above mentioned literature, a collection of scientific articles will be included.

Malmö University provides students who participate in, or who have completed a course, with the opportunity to express their opinions and describe their experiences of the course by completing a course evaluation administered by the University. The University will compile and summarise the results of course evaluations. The University will also inform participants of the results and any decisions relating to measures taken in response to the course evaluations. The results will be made available to the students (HF 1:14).

If a course is no longer offered, or has undergone significant changes, the students must be offered two opportunities for re-examination based on the syllabus that applied at the time of registration, for a period of one year after the changes have been implemented. The syllabus is a translation of a Swedish source text.

If a student has a Learning support decision, the examiner has the right to provide the student with an adapted test, or to allow the student to take the exam in a different format. The syllabus is a translation of a Swedish source text.