Current research projects

These are the current research projects. You can also view the list of previous research projects.
  • Personalized Products Emerging from Tailored User Adapting Logic (Perpetual) (IWT-SBO)

    The ambition of the PERPETUAL project is to develop methods and algorithms that achieve automatic, user-oriented functional demand profiling in support of enhancing product service performance, while requiring less resources through an increased efficiency as a result of well-optimized control policies for a wide range of applications.

  • Learning Control for Production Machines (Lecopro) (IWT)

    The main objective of the LeCoPro project is to establish a knowledge platform on learning control for mechatronic systems in Flanders. To achieve this objective, existing learning control strategies for mechatronic systems will be extended such that a broader class of systems can be handled. Furthermore, learning control strategies from other research domains will be adapted to the specific properties of mechatronic systems and extensively validated in practical test cases. The design procedures for the different learning control algorithms will be consolidated in software toolboxes. During the project, the different learning control strategies will also be compared. Based on this study, the consortium aims to develop a methodology for the design of learning controllers depending on the features of the controlled mechatronic system

  • Language Games voor het Taalonderwijs (IWT)

    This IWT project (PhD grant) aims at offering language learners a platform to optimize their knowledge of particular language system (e.g. Russian aspect, Spanish modality, etc.) through interactions with artificial agents in order to reach optimal communicative success and to improve the general cognitive capacities of the language learner. The existing language game platform that is typically used for agent - agent interactions, is been extended here to host human - agent communication.

  • INSILICO - The in silico Wet Lab (Innoviris-BB2B)

    Many experiments investigating gene expression at the genome-wide scale need to be performed only once and can then be turned into in silico assays. An in silico assay is the combination of a genome-wide database and a dedicated data mining tool to query it with a gene or a group of genes. We propose to develop know-how in in silico assay design that will lay the foundation of a spin-off providing services to the drug and biotech industry R&D.

  • Emergence and Evolution of Biological Symbol Systems (Complexity-NET)

    EvoSym is a collaborative European research project supported under the Complexity-NET 2009 pilot funding call, Interdisciplinary Challenges for Complexity Science. Complexity-NET is the European Network for the Coordination of Complexity Research and Training Activities.

  • Dynamic Speaker Alignment for Interactive Dialog Systems (IWT)

    The goal of this project is to develop and implement a cognitive model of linguistic alignment for interactive dialog. Building on computational models of priming, we will make use of Fluid Construction Grammar's bidirectionality which allows using the same representations for both parsing and production. The alignment model will be tested and evaluated based on a dialog system case study with FCG as its natural language processing frontend.

  • Digging for the Roots of Understanding (DRUST) (EU-ESF)

    The Collaborative Research Project DRUST brings together eminent European research groups that cover the full breadth of Cognitive Science (including cognitive anthropology, cognitive neuroscience, cognitive psychiatry, artificial intelligence, linguistics, philosophy, and psychology) in an interdisciplinary examination of how different types of common ground support interpersonal and intercultural understanding. Communication plays a key role for such an understanding but only to the extent that dialog partners have sufficient common ground. Misunderstandings occur because most dimensions on which common ground can exist are not universally shared and not a priori present.

  • Advancing behavioral and cognitive understanding of speech (ABACUS) (ERC)

    This is a European Research Council starting grant project that investigates which cognitive mechanisms allow us to use combinatorial speech. Human speech is unique because it uses a small set of basic speech sounds to make an unlimited set of possible utterances. This combinatorial structure allows us to make new words (such as “blog” or “app”) easily using speech sounds that we already know. Humans are the only apes that can do this, yet we do not know how our brains do it, nor do we know how exactly our abilities are different from those of other apes. Using novel experimental techniques to investigate human behavior and novel computational techniques to model human cognition, it is the goal of this project to find out how we deal with combinatorial speech.

  • A Cognitive and Computational Investigation of Combinatorial Speech (Innoviris-BB2B)

    This is a project sponsored by the BrainsBack to Brussels initiative of the Brussels region. It intends to investigate the cognitive mechanisms that give us combinatorial speech in order to establish how these mechanisms could have evolved. Combinatorial speech is the ability to make new words by recombining pre-existing speech sounds. Humans are the only apes that can do this, yet we do not know how our brains do it, nor how exactly we differ from other apes, and hence we cannot propose a plausible scenario of how it evolved. Using new experimental techniques to study human behavior and new computational techniques to model human cognition, the project will find out how we deal with combinatorial speech and how this ability may have evolved.