Course syllabus for Interpretable artificial intelligence

Course syllabus adopted 2025-02-13 by Head of Programme (or corresponding).

Overview

  • Swedish nameTolkningsbar artificiell intelligens
  • CodeTME286
  • Credits7.5 Credits
  • OwnerMPCAS
  • Education cycleSecond-cycle
  • Main field of studyEngineering Physics
  • DepartmentMECHANICS AND MARITIME SCIENCES
  • GradingTH - Pass with distinction (5), Pass with credit (4), Pass (3), Fail

Course round 1

  • Teaching language English
  • Application code 11112
  • Maximum participants80 (at least 10% of the seats are reserved for exchange students)
  • Open for exchange studentsYes

Credit distribution

0121 Project 7.5 c
Grading: TH		 7.5 c

In programmes

Examiner

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

Engineering mathematics and (preferably object-oriented) programming.

Aim

The aim of the course is for the students to gain knowledge regarding interpretable methods in artificial intelligence, as well as applications of such methods, especially in high-stakes situations, for example in healthcare, automated driving, finance, and so on. The course also aims to highlight differences between interpretable systems and so-called black-box models, e.g., deep neural networks.

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

  • Define and contrast, on the one hand, black-box models and, on the other, interpretable (glass-box) models in artificial intelligence (AI)
  • Define and describe neuro-symbolic models and methods
  • Discuss and compare different kinds of AI applications
  • Select a suitable model class for a given application
  • Define, implement, and train AI-models (both black-box models and interpretable models) for different applications, e.g., in natural language processing (NLP), data classification, image processing, autonomous robots, and so on.
  • Discuss various ethical aspects related to artificial intelligence

    • Content

  • Black-box models (e.g., deep neural networks)
  • Interpretable models (e.g., rule-based systems, regression models, decision trees, Bayesian methods)
  • Programming, mainly in C# and Python
  • Statistical language models, text processing
  • Data classification, especially text classification
  • Image processing
  • Autonomous robots
  • Other applications (varying content)
  • Ethics of artificial intelligence (applications)

    • Organisation

    The course runs over one quarter and is organized as a series of lectures combined with assignments. The assignments are carried out individually by each student.

    Literature

    A compendium and a selection of scientific papers.

    Examination including compulsory elements

    The examination is based on a set of assignments, solved individually by each student.

    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 about disability study support.