Explainable & Trustworthy Artificial Intelligence

30 September 2024 – 16 December 2024

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. The techniques developed in the domain were and 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.

Artificial Intelligence nowadays are complex and sophisticated algorithms that sometimes make it difficult for the humans to understand and interpret the decisions or suggestions of the AI system.
Explainable AI puts the following properties on the foreground to deliver trust:

  • 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.

This course is a collaboration between UGain and VAIA.

The lessons are intended for anyone who has a good professional familiarity with computer science and who would like to get more insights in techniques that can be applied to achieve explainable and trustworthy Artificial Intelligence. Participants have completed a higher education in computer science or have acquired an equivalent experience.

Participants have programming experience with Python or a related programming language.

The lessons can be followed onsite in the UGain classroom or online live & on demand.

To receive a certificate, one should attend all the lessons and succeed for the final exam. The exam will take place on 27 January 2025.

Scientific Coordination

prof. dr. Femke De Backere, Department of Information Technology, Ghent University – imec & VAIA


  • Tijl De Bie, Department of Electronics and Information Systems, Ghent University
  • Matthias Feys, ML6
  • Femke Ongenae, Department of Information Technology, Ghent University
  • Daniel Peralta Cámara, Department of Information Technology, Ghent University
  • Jonathan Peck, Department of Applied Mathematics, Computer Science & Statistics, Ghent University
  • Yvan Saeys, Department of Applied Mathematics, Computer Science & Statistics, Ghent University
  • Sofie Van Hoecke, Department of Electronics and Information Systems, Ghent University
  • Willem Waegeman, Department of Data Analysis and Mathematical Modelling, Ghent University


In this first lesson, 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

Teachers: Femke Ongenae & Sofie Van Hoecke
Date: 30 September 2024

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
  • Generalized Additive Models (GAMs)
  • Decision Trees
  • Rule-based systems and fuzzy logic

Teacher: Daniel Peralta Cámara
Date: 7 October 2024

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: Yvan Saeys
Date: 14 October 2024

Training machine learning systems can be done before use, i.e. when training it on a stack of pictures first and asking it to make sense of new pictures later. However, it can also be done during use. In the latter scenario the system gets updated whilst it is being used. Sometimes this is necessary because training data is (partially) becoming available after commissioning of the system. Sometimes a system is pretrained on one dataset and the developer wants to retrain the system in order to solve another but related problem, i.e. using a machine vision system that is trained to detect cats to now detect dogs. The developer thus leverages the effort put into the training of the earlier system, hence requiring less training time for the novel system. These and other relations between datasets, their application in training models and the problems we solve with those will be explained in this lesson.

  • Online learning
  • Change detection
  • Transfer learning & domain adaptation (foundation models)

Teacher: Matthias Feys
Date: 21 October 2024

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.

  • Data-driven vs expert-based approaches
  • Finding synergies in data-driven and expert-based approaches
  • Combining expert knowledge and machine learning

Teachers: Femke Ongenae & Sofie Van Hoecke
Date: 4 November 2024

Machine learning systems are extremely fragile: small modifications to their input data can cause them to produce wildly incorrect outputs. These modifications are usually imperceptible or seemingly harmless, making them hard to detect. Such "adversarial perturbations" undermine the trustworthiness of our systems and may pose safety issues under certain circumstances. This lesson explains these problems and what you can do about them.

  • Adversarial learning
  • Evasion attacks & defenses
  • Learning theory

Teacher: Jonathan Peck
Date: 18 November 2024

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 (probabilistic models, calibration methods, set-based representations, conformal prediction, etc.)
  • Second-order uncertainty representations (Bayesian methods, ensemble methods, density-based methods, etc.)

Teacher: Willem Waegeman
Date: 25 November 2024

When training machine learning systems, the training data can be biased, leading to unwanted outcomes. For example, an HR system trained on old hospital personnel data might discriminate against women for doctor positions and against men for nurse positions, due to historical gender biases in these roles. This session will explain these issues, how to avoid them, how to measure bias and what the limitations of avoiding it are. Also advanced bias and fairness issues in large language models, and generative AI more generally, will be covered.

  • Various notions of fairness & impossibility theorem
  • Different types of bias & methods to debias
  • Ethical and legal guidelines
  • Learning fair models
  • Uncovering model bias
  • Biases in Large Language Models and generative AI

Teacher: Tijl De Bie
Date: 2 December 2024

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 session.

  • Pseudonimization
  • K-anonymity
  • Differential privacy
  • Regulation

Teacher: Tijl De Bie
Date: 9 December 2024

During the last session, some specific use cases in the domain of Explainable and Trustworthy AI will be discussed.

Teachers: Tijl De Bie, Matthias Feys, Femke Ongenae & Sofie Van Hoecke
Date: 16 December 2024

Practical info



The fee for onsite participation (in the UGain classroom) is 1.750 euro for all sessions or 200 euro per session (session 1 is mandatory).
This includes the tuition fee, course notes, access to the digital e-learning environment, soft drinks, coffee and sandwiches.


The fee for online participation only is 1.450 euro for all sessions or 165 euro per session (session 1 is mandatory).
This includes tuition fee and online access to the live sessions and the digital e-learning environment with digital course notes and recorded lessons.

All invoices are due in thirty days. All fees are exempt from VAT.


When a participant of a company subscribes for the complete course, a reduction of 20% is given to all additional subscriptions from the same company. In that case, only one invoice is issued per company.

Cancellation policy

Cancellation must be done in writing.

Our cancellation conditions can be consulted on www.ugain.ugent.be/cancellation

Training vouchers

Ghent University accepts payments by KMO-portefeuille (www.kmo-portefeuille.be; authorisation ID: DV.O103194).

Vlaams Opleidingsverlof (VOV)

This course has too few contact hours to qualify for VOV.

Personal data

Last Name* mandatory
First Name*  
E-mail participant*  
Billed privately or on the company?*  

Private data

Licence plate (for access to the parking lot)
Street en number
Postal code

Company data

Company name
E-mail administration (if applicable)
Street en number
Postal code


I subscribe to the course Explainable & Trustworthy Artificial Intelligence:





     1. INTRODUCTION (Mandatory for everyone)


I wish to stay informed about all future UGain-courses.

How were you informed about this course?

Via the UGAIN e-mailing


Cancellation policy

I have read the cancellation policy and I agree to it.*

  • The lessons are given from 17h30 till 21h, with a sandwich break.
  • Location: Ghent University, UGain, building 60, Technologiepark Zwijnaarde.
  • The lessons can be followed onsite or online.
  • Dates may change due to unforeseen reasons.


English is used in all presentations and documentation.


Universiteit Gent
UGent Academie voor Ingenieurs
Els Van Lierde
Technologiepark 60
9052 Zwijnaarde
Tel.: +32 9 264 55 82
With the support of VAIA.

This training can be included in the doctoral training, provided that the doctoral candidate has an approved application for recognition, an 'application for recognition' can be downloaded here.

Anyone who has an approved application can count this training as a 'specialist course' and can expect reimbursement of the registration fee provided that a certificate of attendance can be presented (the doctoral student must have completed at least 15 hours of one course).

You can download the brochure here.