In the road traffic example, the network predicts probabilities for each agent's identity, action and position. At inference, logical rules are evaluated using these predictions. The resulting satisfaction degree is then used to update the network so that future predictions better align with the knowledge constraints, as illustrated in Figure 2.

Growing up as a teenager in the 80's, I witnessed the birth and rise of personal computers firsthand. The Commodore 64 was the first computer to enter our home, and apart from the myriad games we played endlessly, it also made me experiment with BASIC (and basic) programming. Despite my early engagement with computing, at school I was more interested in languages and media (I also wasn't strong enough in maths). So, when it was time to go to university, I chose to study communication sciences at the Faculty of Social Sciences at KU Leuven, Belgium. During my studies, my interest in computers never faded, especially as it coincided with the rise of the Internet and the start of the World Wide Web--an evolution I eagerly followed.

This paper presents a Nonlinear Model Predictive Control (NMPC) scheme targeted at motion planning for mechatronic motion systems, such as drones and mobile platforms. NMPC-based motion planning typically requires low computation times to be able to provide control inputs at the required rate for system stability, disturbance rejection, and overall performance. Although there exist various ways in literature to reduce the solution times in NMPC, such times may not be low enough to allow real-time implementations. This paper presents ASAP-MPC, an approach to handle varying, sometimes restrictively large, solution times with an asynchronous update scheme, always allowing for full convergence and real-time execution. The NMPC algorithm is combined with a linear state feedback controller tracking the optimised trajectories for improved robustness against possible disturbances and plant-model mismatch. ASAP-MPC seamlessly merges trajectories, resulting from subsequent NMPC solutions, providing a smooth and continuous overall trajectory for the motion system. This frameworks applicability to embedded applications is shown on two different experiment setups where a state-of-the-art method fails: a quadcopter flying through a cluttered environment in hardware-in-the-loop simulation and a scale model truck-trailer manoeuvring in a structured lab environment.

Facebook has worked for years to revamp its handling of political ads -- but researchers who conducted a comprehensive audit of millions of ads say the social media company's efforts have had uneven results. The problems, they say, include overcounting political ads in the U.S. -- and undercounting them in other countries. And despite Facebook's ban on political ads around the time of last year's U.S. elections, the platform allowed more than 70,000 political ads to run anyway, according to the research team that is based at the NYU Cybersecurity for Democracy and at the Belgian university KU Leuven. Their research study was released early Thursday. They also plan to present their findings at a security conference next August.

Within the field of process mining, several different trace clustering approaches exist for partitioning traces or process instances into similar groups. Typically, this partitioning is based on certain patterns or similarity between the traces, or driven by the discovery of a process model for each cluster. The main drawback of these techniques, however, is that their solutions are usually hard to evaluate or justify by domain experts. In this paper, we present two constrained trace clustering techniques that are capable to leverage expert knowledge in the form of instance-level constraints. In an extensive experimental evaluation using two real-life datasets, we show that our novel techniques are indeed capable of producing clustering solutions that are more justifiable without a substantial negative impact on their quality.

Companies are finding it hard to grasp the tangible potential of Artificial Intelligence and Machine Learning, and to find ways to cash in on the opportunities. The technology remains rather enigmatic. Let's try to clear a bit of the haze, through a closer look at the reality of AI, including how to identify possible use cases within your organisation. In this session, we'll find out about AI and ML initiatives in business, public entities and academia. We'll hear two real-life cases: on rolling out data mining and AI at FPS Finance, and on how SD Worx uses AI and big data to integrate new services.

Europe is home to 5 of the top 10 universities for computer science in the world. It comes as no surprise, then, that Europe is a hub for ground-breaking AI research. Leading institutes are increasingly tackling real-world challenges using AI. And the trend is not limited to those schools traditionally focused on computer science; business-oriented schools are also recognizing the benefits AI can bring. Those institutes at the cutting-edge of AI research are turning to NVIDIA's DGX Systems, the world's first portfolio of purpose-built AI supercomputers, to provide the computing power they need.

In many real-world classification tasks such as churn prediction and fraud detection, we often encounter the class imbalance problem, which means one class is significantly outnumbered by the other class. The class imbalance problem brings great challenges to standard classification learning algorithms. Most of them tend to misclassify the minority instances more often than the majority instances on imbalanced data sets. For example, when a model is trained on a data set with 1% of instances from the minority class, a 99% accuracy rate can be achieved simply by classifying all instances as belonging to the majority class. Indeed, the problem of learning on imbalanced data sets is considered to be one of the ten challenging problems in data mining research.

Facebook's giving away servers for AI: So what does it get in return? Facebook is distributing 22 high-powered GPU servers to 15 research groups across nine European countries. Just east of the Belgium capital, Brussels, Marian Verhelst's microchip research group at the University of Leuven anxiously awaits a large shipment of supercomputing servers from Facebook's Silicon Valley headquarters. Verhelst, an assistant professor of electrical engineering at the university known as KU Leuven, plans to employ the deep-learning potential of these computers to help develop more advanced processors. As part of a global research partnership to stimulate artificial-intelligence research into deep learning, Facebook is donating 22 GPU-accelerated computer servers to researchers in nine countries across Europe.

This paper proposes a relational learning based approach for discovering strategies in volleyball matches based on optical tracking data. In contrast to most existing methods, our approach permits discovering patterns that account for both spatial (that is, partial configurations of the players on the court) and temporal (that is, the order of events and positions) aspects of the game. We analyze both the men's and women's final match from the 2014 FIVB Volleyball World Championships, and are able to identify several interesting and relevant strategies from the matches.