Course syllabus for Advanced topics in machine learning

The course syllabus contains changes
See changes

Course syllabus adopted 2024-02-05 by Head of Programme (or corresponding).

Overview

  • Swedish nameAvancerade teman i maskininlärning
  • CodeDAT441
  • Credits7.5 Credits
  • OwnerMPDSC
  • Education cycleSecond-cycle
  • Main field of studyComputer Science and Engineering, Software Engineering
  • DepartmentCOMPUTER SCIENCE AND ENGINEERING
  • GradingTH - Pass with distinction (5), Pass with credit (4), Pass (3), Fail

Course round 1

  • Teaching language English
  • Application code 87137
  • Maximum participants100
  • Block schedule
  • Open for exchange studentsNo

Credit distribution

0124 Written and oral assignments 3.5 c
Grading: TH		3.5 c
0224 Examination 4 c
Grading: TH		4 c
  • 28 Okt 2024 pm J DIG
  • 18 Aug 2025 pm J DIG

In programmes

Examiner

Go to coursepage (Opens in new tab)

Eligibility

General entry requirements for Master's level (second cycle)
Applicants enrolled in a programme at Chalmers where the course is included in the study programme are exempted from fulfilling the requirements above.

Specific entry requirements

English 6 (or by other approved means with the equivalent proficiency level)
Applicants enrolled in a programme at Chalmers where the course is included in the study programme are exempted from fulfilling the requirements above.

Course specific prerequisites

To be eligible for the course, a student must have passed a minimum of the following courses:
  • 7.5 credits of programming (Python experience desirable but not absolutely required)
  • 7.5 credits of a data structures and/or algorithms
  • 7.5 credits of basic probability and statistics
  • 7.5 credits of calculus
  • 7.5 credits of linear algebra
  • 7.5 credits of basic machine learning (for example TDA233, MVE440, DAT340)

Aim

This course will focus on advanced topics in machine learning, in order to provide a deep understading of the modern machine learning areas. The students will learn sophisticated machine learning models which are commonly used in real-world applications, and also will learn how to analyze and understand in depth the advanced machine learning models.

Learning outcomes (after completion of the course the student should be able to)

On successful completion of the course the student will be able:
• to learn about modern and advanced machine learning methods and analyze them in different situations
• to read and understand state-of-the-art scientific articles in the field
• to propose and employ suitable models for the complex machine learning tasks
• to be prepared for research and development of advanced machine learning methods

Knowledge and understanding
• to understand in depth the advanced machine learning methods, and learn their practical implications
• to understand some of the main research areas and topics within machine learning
• to learn the way the complex real problems are turned into research questions in machine learning

Competence and skills
• to analyze advanced machine learning and understand why a method may work or may fail
• to deal with the cases where the standard machine learning is not very helpful and needs to be improved
• to be better prepared for research in AI/machine learning
• to read and follow the relevant state-of-the-art research articles

Judgement and approach
• to employ a suitable model w.r.t. the assumptions and analyze the different aspects such as performance and effectiveness
• to learn how machine learning models can be further developed to satisfy the requirements
• to distinguish some of the main research areas in machine learning, the corresponding challenges and the current approaches to solve them

Content

The course is focused on advanced theory, methods and mathematics of machine learning.

The course content is the following:
• Theoretical machine learning and the computational aspects
• Sequential decision making
• Online learning/Active learning/Multi-armed bandits
• Markov decision processes
• Reinforcement learning
• Relevant advanced deep learning (Deep Neural Network) models

Organisation

Lectures and assignments.

Literature

See course homepage.

Examination including compulsory elements

The course is examined by assignments and a written hall examination.

The course examiner may assess individual students in other ways than what is stated above if there are special reasons for doing so, for example if a student has a decision from Chalmers on educational support due to disability.

The course syllabus contains changes

  • Changes to course rounds:
    • 2024-09-06: Examinator Examinator Morteza Haghir Chehreghani (haghir) added by Viceprefekt
      [Course round 1]