2026's Seminars
[ELEN] 2026-05-05 (09:30) : Modeling reconfigurable intelligent surfaces
At Shannon
Speaker :
Enrico Maria Vitucci (University of Bologna)
Abstract : Enrico Maria Vitucci will share some insights from his work on deterministic propagation modelling and reconfigurable intelligent surfaces. The presentation will remain at a fundamental level, so even if you are not an expert in his specific areas of focus, you should be able to follow along easily! He also plans to touch upon current challenges and exciting future research directions in the field.
[LINGI2399] 2026-04-16 (10:45) : Quantum Computing
At BARB94
Speaker :
Eric Michiels (IBM)
Abstract : Quantum Computing is rapidly moving onto the strategic agenda of organizations worldwide. It is designed to tackle complex problems and serves as a complement, not a replacement, to Classical Computing. What truly sets Quantum Computing apart? What are the key characteristics of its hardware, software, and applications? Which hardware architectures exist, and how are Quantum Algorithms developed? And what skills will professionals need in the new "Quantum Era"?
The speaker will explore short-, mid-, and long-term use cases, look at early adopters, and examine the synergy between Quantum Computing and AI. You will also discover how both junior and senior professionals can begin their Quantum Journey.
[INGI] 2026-04-16 (13:00) : No evaluation without fair representation: Impact of label and selection bias on the evaluation, performance and mitigation of classification models
At BARB 94 (Hall Sainte-Barbe)
Speaker :
Magali Legast (ICTEAM)
Abstract : Bias can be introduced in diverse ways in machine learning datasets, for example via selection or label bias. Although these bias types in themselves have an influence on important aspects of fair machine learning, their different impact has been understudied. In our work, we empirically analyze the effect of label bias and several subtypes of selection bias on the evaluation of classification models, on their performance, and on the effectiveness of bias mitigation methods. We also introduce a biasing and evaluation framework that allows to model fair worlds and their biased counterparts through the introduction of controlled bias in real-life datasets with low discrimination. Using our framework, we empirically analyze the impact of each bias type independently, while obtaining a more representative evaluation of models and mitigation methods than with the traditional use of a subset of biased data as test set. Our results highlight different factors that influence how impactful bias is on model performance. They also show an absence of trade-off between fairness and accuracy, and between individual and group fairness, when models are evaluated on a test set that does not exhibit unwanted bias. They furthermore indicate that the performance of bias mitigation methods is influenced by the type of bias present in the data. Our findings call for future work to develop more accurate evaluations of prediction models and fairness interventions, but also to better understand other types of bias, more complex scenarios involving the combination of different bias types, and other factors that impact the efficiency of the mitigation methods, such as dataset characteristics.
[INMA] 2026-04-14 (14:00) : High order deterministic and stochastic optimization without evaluating the objective function
At Euler building (room A.002)
Speaker :
Philippe Toint (Université de Namur)
Abstract : We first motivate OFFO methods, that is methods for optimization without computing the objective function's value. We then show that such methods are applicable for unconstrained minimization of nonconvex functions (both in the deterministic and stochastic frameworks) and give a few examples from deep learning applications. We then move on to the case where the problem has general equality and inequality constraints, propose an OFFO algorithm for this case and analyze its global convergence rate in the deterministic case. We conclude by presenting some numerical illustration of the proposed method. This is a Joint work with S. Gratton, S. Bellavia and B. Morini.
[LINGI2399] 2026-04-09 (10:45) : How LLMs will change IT jobs
At BARB94
Speaker :
Tim Paridaens (Deloitte)
Abstract : The rise of Large Language Models (LLMs) is poised to revolutionize the IT job landscape. In domains such as automated coding assistance, automated testing, customer support automation or cybersecurity advancements, LLMs already provide today advanced capabilities that efficiently support IT staff in their daily operations. The speaker will share Deloitte’s experience using LLMs to support IT functions and highlight measured gains and identified limitations.
Seminars
Subscribe (ICS)
INMA Contact Info
Mathematical Engineering (INMA)
L4.05.01
Avenue Georges Lemaître, 4
+32 10 47 80 36
secretaire-inma@uclouvain.be
Mon – Fri 9:00A.M. – 5:00P.M.
JOIN US