Projects
Extreme High Speed ADC KU Leuven
Structural funding of the DSI institute Hasselt University
Syntactico-semantic generalisation operators for learning large-scale usage-based construction grammars Vrije Universiteit Brussel
and constructionist approaches to language have by now become a mainstream paradigm for
linguistic research. Constructionist theories of language consider form-meaning mappings, called
constructions, to be the fundamental building blocks of human languages. Empirical studies have
shown that constructions are learnt ...
The Holographic Universe of String Theory KU Leuven
The most challenging problems in theoretical physics are related to the dynamics of strongly coupled systems and the puzzles of black hole horizons. Many of these open questions are brought together in sharp focus by the holographic correspondence which relates the physics of gravitational systems to that of quantum fields. The main objective of this project is to take major steps towards addressing the challenges associated with black holes ...
ABN HaFreeS Feasibility. University of Antwerp
Robotic assisted multi-sensor access for cochlear diagnostics and therapies KU Leuven
ReSOS: Resource Secure Operating System KU Leuven
Begging and homelessness in the Brussels Capital Region: the intersection between multidimensional deprivation and (in)visibility KU Leuven
The Brussels Capital Region is an example of the “urban paradox”: a centre of capital growth, income acquisition and innovation, but also of harsh living conditions, substandard housing and poverty. Concurrently, there is little reliable evidence to underpin policy regarding (extreme) poverty. Together with stakeholders, this project aims to fill the gap between the visibility, public concerns and policy importance of the problems, on the one ...
Resource-Constrained Training of Deep Neural Networks for Industrial Computer Vision Applications KU Leuven
Deep neural networks have demonstrated exceptional performance in various computer vision tasks such as classification, detection, and segmentation. However, training these networks remains challenging, particularly in resource-constrained industrial settings.
A major obstacle lies in the computational and memory demands of training deep neural networks, which pose significant constraints in low-powered embedded systems used in ...