Explainable AI (XAI) – Concepts, Tools and Applications

Topic: Explainable AI (XAI) – Concepts, Tools and Applications

When: 25 February 12.00 to 13.00

Where: Online

Speaker: Sule Tekkesinoglu, Software Engineering Research Group, Lund University

Moderator: Per Runeson, Software Engineering Research Group, Lund University

Spoken language: English

Abstract

As AI continues to advance, the need to understand how these systems make decisions is becoming increasingly critical. This seminar introduces the growing field of Explainable Artificial Intelligence (XAI), which aims to make AI systems more transparent, interpretable, and accountable. We will explore why explainability matters not only for developers and researchers but also for non-technical users. Core XAI concepts, including local and global explanations and model-specific and model-agnostic methods, will be introduced, along with some application examples. We will also discuss how explanations are presented and evaluated, as well as the challenges that remain in this evolving field.

Speaker Bio: Sule Tekkesinoglu is a researcher at Lund University with a focus on machine learning, explainable artificial intelligence (XAI), and human-machine collaboration. Prior to joining Lund, she was a postdoctoral researcher at the Oxford Robotics Institute (ORI), where she explored explainability in the context of autonomous driving systems. She earned her PhD from Umeå University, where her work centred on developing and presenting intelligible explanations for predictions made by black-box algorithms. 

Her research aims to bridge the gap between AI decision-making and human understanding through explainable AI approaches applied in real-world settings.