Course syllabus for Structured machine learning

The course syllabus contains changes
See changes

Course syllabus adopted 2024-02-01 by Head of Programme (or corresponding).

Overview

  • Swedish nameStrukturerad maskininlärning
  • CodeDAT625
  • 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 87138
  • Maximum participants60 (at least 10% of the seats are reserved for exchange students)
  • Minimum participants5
  • Block schedule
  • Open for exchange studentsYes

Credit distribution

0124 Written and oral assignments 7.5 c
Grading: TH		7.5 c

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

Experience of Python programming is essential, prior experience with a modern machine learning library is highly recommended.

Knowledge equivalent to at least three of the following course's content:
Linear algebra (7.5 credits), numerical mathematics or scientific computing (7.5 credits), calculus (7.5 credits), or statistical mechanics/thermodynamics (7.5 credits).
 
One course in computational or mathematical statistics (7.5 credits) and one in machine learning (7.5 credits).

Students are recommended to take the course in second year of their master's program.  

Aim

The aim of the course is to familiarize students with the use of structure of data, and data generating processes, and how this information can be used to inform machine learning architecture design and training.
The course focuses on building a strong understanding of the underlying concepts and applying them in a practical setting. There will be a particular focus on applications in natural sciences.

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

After the course the student is expected to be able to:

Knowledge and understanding
  • Summarize data generation processes as a schematic figure
  • Distinguish non-equilibrium and equilibrium data.
  • List examples of structured machine learning architectures
  • Explain the basic principles of structured learning architectures
Skills and abilities
  • Conceptualize a machine learning system which uses structure from a data generating process
  • Implement machine learning models to approximate structure endowed by a given data generation process
  • Design a small-scale machine learning research project in structured machine learning.
Judgment and approach
  • Judge recent scientific reports on machine learning research projects using structure in data or data generating process.
  • Appraise small-scale research projects within structured machine learning using structure in data or data generating process.

Content

The course will integrate theoretical lectures with assignments. The course is comprised of three different components:

1. What do we know
  • What is ‘structure’?
  • Data generating processes.
  • Symmetries and convolutions and their abstract representations

2. How do we use what we know
  • Constructing neural networks that use natural symmetries.
  • Constructing models of data generating processes
  • Dealing with Irregular data, for example: Images, graphs, molecules, sequences, and manifolds

3. Applications
  • Sampling unnormalized probability distributions
  • Estimating potential energy functions
  • Classifying molecules.

Organisation


Literature

Lecture notes/hand-outs. Primary literature.

Examination including compulsory elements

Hand-ins, take-home projects, peer-assessment and essay assignment.

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:
    • 2024-11-28: Block Block D added by Elin Johansson
      [Course round 1]
    • 2024-05-03: Examinator Examinator Simon Olsson (simonols) added by Viceprefekt
      [Course round 1]
    • 2024-03-26: Added to program plan [Course round 1] added to programme plan for MPDSC grade 1 by UOL, administratör
  • Change made on course round in programme overview:
    • 2024-03-26: Grouping Grouping changed by UOL, administratör
      [Compulsory elective. Compulsory elective course. (DAT441, DAT450, DAT465, EEN100, MVE172, RRY025, SSY098, SSY316, SSY340, TMA522, TMA882, TMS016, TMS088). Requirements 2 course(s). In MPDSC Year 1] DAT625 added to group