Program Overview

Master's Programme, Machine Learning

The Master's Programme in Machine Learning is designed to provide students with a comprehensive understanding of the principles and techniques of machine learning. The programme is tailored to meet the needs of students who wish to pursue a career in this field.

Programme Objectives

The programme objectives are to provide students with a deep understanding of the theoretical foundations of machine learning, as well as practical skills in the design, implementation, and application of machine learning algorithms.

Extent and Content of the Programme

The programme consists of two years of full-time study, with a total of 120 ECTS credits. The programme is divided into two study years, with each year consisting of four study periods.

Study Year 1

The first study year provides a foundation in the principles of machine learning, including supervised and unsupervised learning, neural networks, and deep learning.

Study Year 2

The second study year provides advanced courses in machine learning, including specialized courses in areas such as computer vision, natural language processing, and robotics.

Programme Structure

The programme consists of mandatory and conditionally elective courses. The mandatory courses provide a foundation in the principles of machine learning, while the conditionally elective courses allow students to specialize in areas of their interest.

Mandatory Courses

• DD2301 Program Integrating Course in Machine Learning (3.0 credits)
• DA233X Degree Project in Computer Science and Engineering, specializing in Machine Learning, Second Cycle (30.0 credits)

Conditionally Elective Courses

The conditionally elective courses are divided into two categories: Theory and Application Domain.

Theory

• Machine Learning: EL2805, DD2437, ID2223, ID2222, EQ2341, DD2601, DD2610
• Mathematics: SF1811, EL2320
• Statistics & Probability: SF2930, SF2940, SF2943, DD2447, DD2420

Application Domain

• Computer Vision: EQ2425, DD2423, DD2424
• Databases/Information Retrieval: DD2477
• Language Processing; Speech & Text: DD2417, DT2112, DT2119
• Visualization: DD2257
• Computational Biology: DD2435, DD2402, DD2435, DD2401
• Robotics: DD2438, DD2410, DD2419, DD2411, DD2438, DD2410, DD2411
• Sound: DT2470

Course List

The following courses are part of the programme:

• DD2257 Visualization (7.5 credits)
• DD2410 Introduction to Robotics (7.5 credits)
• DD2423 Image Analysis and Computer Vision (7.5 credits)
• DD2430 Project Course in Data Science (7.5 credits)
• DD2435 Mathematical Modelling of Biological Systems (9.0 credits)
• DD2447 Statistical Methods in Applied Computer Science (6.0 credits)
• DD2601 Deep Generative Models and Synthesis (7.5 credits)
• DD2610 Deep Learning, advanced course (7.5 credits)
• DT2470 Music Informatics (7.5 credits)
• EL2320 Applied Estimation (7.5 credits)
• EL2805 Reinforcement Learning (7.5 credits)
• EQ2425 Analysis and Search of Visual Data (7.5 credits)
• ID2222 Data Mining (7.5 credits)
• ID2223 Scalable Machine Learning and Deep Learning (7.5 credits)
• SF1811 Optimization (6.0 credits)
• SF2940 Probability Theory (7.5 credits)
• DD2411 Research project in Robotics, Perception and Learning (15.0 credits)
• DD2420 Probabilistic Graphical Models (7.5 credits)
• DD2437 Artificial Neural Networks and Deep Architectures (7.5 credits)
• DD2438 Artificial Intelligence and Multi Agent Systems (15.0 credits)
• SF2930 Regression Analysis (7.5 credits)

Recommended Courses

The following courses are recommended for students who wish to extend their competency and knowledge in Computer Science and Software Engineering:

• DD2395 Computer Security (6.0 credits)
• ID2221 Data-Intensive Computing (7.5 credits)
• IK2215 Advanced Internetworking (7.5 credits)
• DD1388 Program System Construction Using C++ (7.5 credits)
• DD2352 Algorithms and Complexity (7.5 credits)
• DD2448 Foundations of Cryptography (7.5 credits)
• DH2642 Interaction Programming and the Dynamic Web (7.5 credits)
• IK2221 Networked Systems for Machine Learning (7.5 credits)
• IK2227 Network Systems with Edge or Cloud Datacenters (7.5 credits)

Eligibility and Selection

The eligibility and selection criteria for the programme are based on the student's academic background and qualifications.

Implementation of the Education

The programme is implemented through a combination of lectures, tutorials, and project work. The teaching is done by experienced faculty members who are experts in their fields.

Degree Project

The degree project is a mandatory part of the programme, and it provides students with the opportunity to apply their knowledge and skills in a real-world setting. The degree project is supervised by an experienced faculty member, and it is evaluated based on its academic quality and relevance to the field of machine learning.