Explainable & Trustworthy AI
Artificial Intelligence consists of complex and sophisticated algorithms that sometimes make it difficult for humans to understand and interpret the decisions or suggestions of the AI system. This course on Explainable AI looks into the different aspects related to (creating) trust in AI.
Practical information:
Want to register?
- Register until: 21 Apr 2026
- Prerequisites: Higher education in computer science or equivalent experience programming experience with Python or related programming language
- Price: €1.450 online
Georganiseerd door:
Artificial Intelligence (AI) has come a long way since its first use and application many decades ago. The use of AI and Machine Learning have seen an immense uptake in the 21st century and the techniques are successfully applied to a wide variety of problems, both in academia, private and public industry. As this domain became more and more established in recent years, new challenges arose because the rationale and outcomes cannot always be followed by people.
Explainable AI puts the following properties of trust in AI on the foreground:
- Gaining trust by explaining for example the characteristics of AI output.
- By explaining an AI technique understanding will increase, allowing to investigate if the technique can be transferred to another domain or problem.
- Informing a user about the workings of an AI model so that there is no misinterpretation.
- Confidence of users can be established by using AI models that are explainable, stable but also robust.
- When explaining AI models issues concerning privacy awareness come into play. Private data should not be exposed by the models.
- It is important that actions can be explained. How have we come to specific outcomes and how could we change them?
- Nowadays, a wide variety of people from different background come into contact AI, it is important that they all understand why the system is behaving in such a manner and offer explanations tailored to their needs.
Programme
Introduction, 22 April 2026
In this first module, we give a short recap of the basics, followed by the explanation of some general terms that are used in the domain of explainable and trustworthy Artificial Intelligence. This introduction will end with the definition of the challenges within this domain.
- Recap the basics: AI, ML and statistics
- Different types of ML: white-box & black-box
- Interpretability vs Explainability
- Human Uncertainty vs Model Uncertainty
- Challenges
Teacher: prof. dr. Sofie Van Hoecke, Department of Electronics and Information Systems, Ghent University & prof. dr. Femke Ongenae, Department of Information Technology, Ghent University
White box models, 29 April 2026
In this module, focus is given to white box models. While black box models offer higher accuracy, white box models are easier to explain and to interpret, unfortunately this leads to a lesser predictive capacity. In the area of white box models, several different approaches will be highlighted:
- Linear Regression
- Decision Trees and Rule Sets
- Generalized Additive Models (GAMs)
Teacher: prof. dr. Yvan Saeys, Department of Mathematics, Computer Science and Statistics, Ghent University
Interpretability & Explainability, 6 May 2026
Machine learning systems build models that learn to automate complex tasks by learning from examples. How to get insights into how these models work depends on the type of algorithm used. Getting insights into how our models work can be done by looking at how the model works in general (interpretability), versus how a specific prediction of the model was computed (explainability). Additional hypothetical “What if” questions can be asked to allow for counterfactual reasoning, adding to the toolkit of explainability methods.
- Interpretability versus explainability
- Counterfactuals
- Model distillation
- Dependency plots
- Saliency maps
Teacher: prof. dr. Yvan Saeys, Department of Mathematics, Computer Science and Statistics, Ghent University
Supply Chains & Operations, 13 May 2026
Since most AI systems are still black boxes, transparency in the AI supply chain is a foundational property of trustworthy AI. Knowing where a model comes from, what data it was trained on, an how it was tested is key to building confidence in the model itself.
We introduce the concept of an AI Bill of Materials (AI BoM), inspired by software supply chain practices, to document model lineage, training data provenance, and environment details.
By making these elements verifiable, AI BoMs enable explainability, accountability, and compliance with emerging regulations such as the EU AI Act. Open source AI models play an important role in creating more transparency, and confidential computing helps safeguard sensitive data during training and inference.
Attendees will gain practical insights into techniques that strengthen trust in AI systems without compromising innovation.
Teacher: dr. Merlijn Sebrechts, Department of Information Technology, Ghent University
Hybrid AI, 20 May 2026
The oldest forms of machine learning entail rule engines that were hand programmed. Newer forms entail algorithms searching for connections themselves. The first are great in explaining how they reach their conclusions. The latter sometimes give superior predictions, being a lot less brittle, but lack that explainability. To get the best of both worlds, these approaches are sometimes combined. Moreover, allowing an expert to guide a machine learning system can sometimes lead to yet again superior predictions. This module explains how.
- Data-driven vs expert-based approaches
- Finding synergies in data-driven and expert-based approaches
- Combining expert knowledge and machine learning
Teacher: prof. dr. Sofie Van Hoecke, Department of Electronics and Information Systems, Ghent University & prof. dr. Femke Ongenae, Department of Information Technology, Ghent University
Robustness, 27 May 2026
The output of a machine learning system depends on the data used as input. Often the needed amount and structure of that data is overlooked. However, machine learning systems can be combined to generate additional data or to finetune each other. Nevertheless, malicious additions to your training data can corrupt your system and even a well-trained system can be deceived. This module explains these issues and what you can do about them.
- Data quality & quantity
- Adversarial learning
- Poisoning attacks & defenses
- Learning theory
Teacher: dr. Jonathan Peck, Department of Applied Mathematics, Computer Science & Statistics, Ghent University
Uncertainty, 3 June 2026
The notion of uncertainty is of major importance in machine learning and constitutes a key element of modern machine learning methodology. In recent years, it has gained attention due to the increasing relevance of machine learning for practical applications, many of which are coming with safety requirements. In this regard, new problems and challenges have been identified by machine learning scholars, many of which call for novel methodological developments. Indeed, while uncertainty has a long tradition in statistics, and many useful concepts for representing and quantifying uncertainty have been developed on the basis of probability theory, recent research has gone beyond traditional approaches and also leverages more general formalisms and uncertainty calculi.
- Aleatoric and epistemic uncertainty
- First-order uncertainty representations
- Second-order uncertainty representations
Teacher: prof. dr. Willem Waegeman, Department of Data Analysis and Mathematical Modelling, Ghent University
Bias & Fairness, 10 June 2026
When training machine learning systems, the training data can be biased, leading to unwanted outcomes, i.e. an HR system trained on old hospital personnel data now stating that women might be unlikely good candidates for doctor positions. This module will explain these issues, how to avoid them, how to measure bias and what the limitations of avoiding it are.
- Various notions of fairness & impossibility theorem
- Different types of bias & methods to debias
- Ethical guidelines
- Learning fair models
- Uncovering model bias
Teacher: prof. dr. Tijl De Bie, Department of Electronics and Information Systems, Ghent University
Privacy, 17 June 2026
Sometimes the quality of machine learning system outputs and privacy are at odds and need to be balanced. However, there are techniques that allow the training of machine learning systems on privacy sensitive data, without exposing the data itself. Those techniques and relevant regulation on these practices are explained in this module.
- Pseudonimization
- K-anonymity
- Differential privacy
- Regulation
Teacher: prof. dr. Tijl De Bie, Department of Electronics and Information Systems, Ghent University
Use cases, 24 June 2026
During this module, some specific use cases in the domain of Explainable and Trustworthy AI will be discussed.