Seminar Human-Centered AI – Human-Computer Interaction meets Artificial Intelligence

Explainable Artificial Intelligence (xAI) aims to make AI systems more transparent, interpretable, and understandable to humans, supporting trust, accountability, and effective human-AI interaction.

This seminar explores the fundamental concepts, methods, and challenges of xAI, with a particular focus on human-centered explainability. It examines different approaches to generating explanations, including intrinsic and post-hoc methods, global and local explanations, and model-specific versus model-agnostic techniques.

Beyond technical aspects, the seminar investigates how explanations can be designed to address the needs, expectations, and cognitive characteristics of different users. Particular attention is given to the relationship between explainability, human understanding, trust, and decision-making.

Through a review and critical analysis of scientific literature, students will explore state-of-the-art approaches, methodologies, and tools for designing and evaluating human-centered xAI systems.

The seminar is organized around an individual research topic related to explainable AI, with an emphasis on human-centered approaches. Students’ research topics are defined each year.

Students will conduct a scientific literature review to investigate state-of-the-art methods, techniques, frameworks, and applications. They will critically analyze existing approaches, compare their strengths and limitations, and identify relevant research challenges.

The seminar includes:

  • Research work: Literature review and critical analysis of a selected topic, based on relevant scientific publications.
  • Supervision: Regular opportunities for individual meetings with supervisors to discuss progress and research directions.
  • Mid-term and final presentation: Presentation of preliminary findings, literature review, and planned work (mid-term) and overall synthesis and discussion of the research findings (final).
  • Optional practical work: Development of a demonstrator or prototype to illustrate, apply, or compare selected xAI techniques.

Please note that the number of places available for this seminar is limited.

Details

Code 33685
63685
Type Seminar
ECTS 5
Site Fribourg
Track(s) T3 – Visual Computing
T6 – Data Science
Semester S2027

Teaching

Learning Outcomes

Upon successful completion of the seminar, students will be able to:

  • Understand the fundamental concepts, motivations, and challenges of explainable AI.
  • Identify and compare different xAI approaches, techniques, and tools, including intrinsic/post-hoc and global/local explanations.
  • Analyze the role of human factors, user needs, and cognitive processes in the design of AI explanations.
  • Critically evaluate xAI methods from both technical and human-centered perspectives, considering interpretability, usability, trust, and effectiveness.
  • Conduct a scientific literature review, synthesize research findings, and communicate results through a scientific report and oral presentation.
Lecturer(s) Elena Mugellini
Omar Abou Khaled
Language english
Course Page

The course page in ILIAS can be found at https://ilias.unibe.ch/go/crs/3684770.

Schedules and Rooms

Period On Appointment

Additional information

Comment

First Lecture
Please contact Elena Mugellini (Elena.Mugellini@hefr.ch) to select the date of the first meeting.