Proceed to contents
Thematic webinar

AI Explainability: What is it, What it isn't and Where are we now?

5 Sep 2025 11:00 - 12:00
Get familiar to what works and what doesn't when looking into methods for justifying outputs produced by AI systems,

Practical information:

5 Sep 2025 11:00 - 12:00
1 hours
Link to the webinar is distributed upon registration
English
Target audience: Professionals and Academic Individuals interested on justifying the outputs produced by AI systems

Want to register?

  • Prerequisites: Familiarity with general Machine Learning
  • Price: Free
More info & registration ⇗

Georganiseerd door:

By now Artificial Intelligence (AI) and Machine Learning (ML) have proven to be an effective means to improve several processes from Industry. Following the "Right to Explanation" stated in the EU GDPR, high-stakes AI/ML-based systems must provide a means to access the logic behind the decision-making process that determine the outputs produced by such systems.

In this talk we will discuss some of the families of existing explanation methods setting the focus on some of the most representative instances. We will cover evaluation protocols commonly used to validate the output produced by such methods. We will conclude with a discussion of the current state of the field, weak aspects to keep present and potential steps forward.

Teacher / speaker

José Oramas

José Oramas is an Assistant Professor at the Internet Data Lab (IDLab) a joint research lab between the University of Antwerp and IMEC. He received his Ph.D. at the Center for Processing Speech and Images (ESAT-PSI)of KU Leuven in April 2015. Earlier he received his engineering degree from Escuela Superior Politecnica del Litoral in Ecuador. During his Ph.D. he conducted research on understanding how groups of elements from the image (objects, object-parts, image regions, trajectories, etc.) interact and how the relationships between them can be exploited to improve artificial visual perception problems. This fueled his interest towards investigating exploratory/explanatory models that can identify informative intermediate representations and use them as means to justify the predictions that they make.

Research Interests: Representation Learning, Interpretability and Explainability, Multiple Instance Learning, Machine Learning, Deep Learning and Computer Vision

Claude AI Cowork

15 September 2026

Workshop - Brussels - IT for Humanity

Machine learning and deep learning fundamentals

18 November 2026

Workshop - Leuven - VIB, Training geselecteerd in de Belgische AI Factory Antenna (AIFA)