OT-AIAT 20

Introduction to Explainable AI (XAI): Motivation, Concepts & Challenges

Zielgruppe

Everyone is welcome who wants to get an understanding of how and why AI systems make decisions.

This webinar is open and free of charge for all participants from academia, industry, and public administration fromEUand/orEuroHPC JUmember countries.

Inhalt und Ziele

As Artificial Intelligence (AI) becomes increasingly woven into our daily lives, the need to understand how and why these systems make decisions has never been more important.

This webinar offers an accessible introduction to the field of XAI: what it is, why it matters, and where its biggest challenges lie. We will begin with the motivations driving the demand for transparency in AI, why AI models are often called black-boxes, from fairness and accountability to safety and trust. Participants will then be guided through the core ideas behind XAI, exploring how explainability techniques help us open the “black box” of modern machine learning. Finally, we will discuss real-world limitations and open questions that researchers and practitioners continue to face.

This session is designed for a broad audience, no deep technical background required. A dedicated hands-on XAI workshop will follow for data scientists and ML enthusiasts interested in experimenting with tools, techniques, and practical workflows.

Agenda

11:00 Welcome & Presentation of AI Factory Austria AI:AT

11:05 Introduction to Explainable AI (XAI): Motivation, Concepts & Challenges

11:50 Questions & Discussion

Trainer

Zeit und Ort

Seminarnummer:

OT-AIAT 20

Trainingsform:

Online-Tr. / Webinar

Dauer:

1 Tag(e) (1 Stunden)

Termin:

17.11.2026

Stundenplan:

10:00 - 11:00

Ort:

Online

Anmerkungen

Entry level & prerequisites

Beginner – no prior AI knowledge is required.

Language

English

Speaker

Anahid Wachsenegger (AIT Austrian Institute of Technology GmbH)
Anahid Wachsenegger is a data scientist at the AIT Austrian Institute of Technology, specializing in artificial intelligence, explainable machine learning, data-driven modeling, and time-series analysis across domains such as forestry and mobility data science. She holds a Master’s degree in Computational Intelligence from TU Wien and also served as an associate lecturer in Media and Digital Technologies at the University of Applied Sciences St. Pölten. She is passionate about developing trustworthy, transparent AI systems, applying data science to real-world challenges, and supporting students and practitioners in understanding and responsibly using modern AI technologies.

Organisation

Seminarleitung:

Buchwinkler David BA MA

Sekretariat:

Fröhlich Elisabeth