All Years Seminars
[INGI] 2026-02-12 (10:45) : Data Analytics : Data-driven consumer centric services
At BARB 94
Speaker :
Christophe Robyns (Agilytic)
Abstract : Massive internal and external data are available to better understand customer sentiment and anticipate or influence his behaviour. Having experience both in commercial and non-commercial organisations, the speaker will explain how data can be used to influence customer behaviour and enhance services. The speaker will also present steps that are required to build a big data platform that provides reliable and up-to-date information.
[ELEN] 2026-02-12 (13:00) : Mixed-signal neuromorphic circuits and systems for extreme-edge computing
At Nyquist
Speaker :
Dr. Ariana Rubino (ETH Zurich)
Abstract : Brain-inspired computing architectures offer a promising solution for
integrating Internet of Things (IoT) sensors with intelligent local
processing in edge computing applications. In particular, mixed-signal
event-based neuromorphic designs inherently meet key requirements of
edge computing: power efficiency, compactness, low latency, real-time
processing, and adaptability via on-chip learning.
Despite these advantages, several challenges remain. These include the
development of powerful and effective spike-based learning mechanisms,
the adoption of advanced Complementary metal-oxide-semiconductors (CMOS)
technology nodes, and the significant silicon area required to implement
neural dynamics with long time constants and synaptic plasticity.
In my talk, I will showcase the research conducted during my PhD to
advance the state of the art in mixed-signal neuromorphic processors for
edge computing. In particular, I will highlight the potential of
multi-compartment neuron models to enable dendritic spike-based learning
rules driven by target activities - an approach well suited to compact
and resource constrained edge devices. To support the development of
more compact and low-power systems, and to address the limitations of
scaled bulk-CMOS technologies, I will present our investigation into
Fully Depleted-Silicon on Insulator (FDSOI) transistor technology for
neuromorphic circuit design, demonstrating improved energy efficiency,
reduced mismatch, and better support for long synaptic dynamics.
Finally, to further optimize compactness at the synaptic array, I will
discuss emerging memory technologies, with a focus on energy-efficient
edge-compatible Ferroelectric Tunneling Junction (FTJ) memristive
synapses.
For each of these three aspects, I will present the mixed-signal
neuromorphic processors I designed and/or contributed to - ranging from
prototype test platforms to large-scale multi-core architectures - along
with both circuit-level simulation results and chip-level measurement
data.
[INMA] 2026-02-10 (14:00) : The Ellipsoidal Separation Machine
At Euler building (room A.002)
Speaker :
Antonio Frangioni (Università di Pisa)
Abstract : We propose the -- to the best of our knowledge -- first fully functional implementation of the "Separation by a Convex Body" approach first outlined in [Grzybowski et al., Optimization Methods and Software, 2005] for classification, separating two data sets using an ellipsoid. A training problem is defined that is structurally similar to the Support Vector Machine (SVM) one, thus leading to call our method the Ellipsoidal Separation Machine (ESM). Like SVM, the training problem is convex, and can in particular be formulated -- via a set of not entirely obvious reformulation tricks -- as a Semidefinite Program (SDP). However, practical classification tasks produce rather large SDPs, solving which by means of standard SDP approaches (be them IP-or first-order based) does not scale. As an alternative, a nonconvex formulation is proposed that is amenable to a Block-Gauss-Seidel approach alternating between a much smaller SDP and a simple separable Second-Order Cone Program. For the purpose of the classification approach the reduced SDP can even be solved approximately by relaxing it in a Lagrangian way and updating the multipliers by fast subgradient-type approaches. A characteristic of ESM is that it necessarily defines "indeterminate points", i.e., those that cannot be reliably classified as belonging to either one of the two sets. This makes it particularly suitable for Classification with Rejection (CwR) tasks, whereby the system explicitly indicates that classification of some points as belonging to one of the two sets is too doubtful to be reliable. We show that, in many datasets, ESM is competitive with SVM -- with the kernel chosen among the three standard ones and endowed with CwR capabilities using the margin of the classifier -- and in general behaves differently. Thus, ESM provides another arrow in the quiver when designing CwR approaches, although more work would be needed to scale it to really large datasets.
[INGI] 2026-02-05 (13:00) : Fair Tabular Data Generation: an Approach using Autoregressive Decision Trees
At Nyquist Maxwell a.164
Speaker :
Benoît Ronval (ICTEAM)
Abstract : In both research and industry, tabular data is among the most widely used data types. Represented using instances (rows) with features (columns), such data is easy for humans to interpret and readily usable by most machine learning algorithms.
Despite its large usage, acquiring new tabular data can be challenging. Data collection can require access to private sources or large-scale surveys, which may be costly and may suffer from low response rates. Moreover, real-world tabular datasets frequently exhibit bias, leading machine learning models to produce unfair classifications for certain subgroups, particularly with respect to sensitive attributes such as the nationality or the education level of a person.
In this seminar, I will present our new method TabFairGDT, which aims to generate data that can reduce fairness concerns in the predictions of machine learning models trained on this data. The approach leverages decision trees in an autoregressive generation framework, including a fairness optimization step. I will also discuss the advantages of decision trees for tabular data generation and present experimental results, including classification performance, fairness metrics, and data quality analyses.
[INMA] 2026-02-03 (14:00) : IRKA Is a Riemannian Gradient Descent Method
At Euler building (room A.002)
Speaker :
Petar Mlinarić (University of Zagreb)
Abstract : Large-scale systems frequently arise in applications involving partial differential equations or network dynamics. Model order reduction seeks to replace a large-scale system with a reduced-order model, enabling faster simulations with minimal loss of accuracy. The Iterative Rational Krylov Algorithm (IRKA) is a well-known method for model order reduction of linear time-invariant systems, originally formulated as a fixed-point iteration. In this talk, we show that IRKA can be interpreted as a Riemannian gradient descent method with a fixed step size on the manifold of rational functions of fixed degree. This geometric perspective motivates the application of other Riemannian optimization techniques to the same problem. We illustrate the effectiveness of these approaches through numerical examples.
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