Tom Viering Assistant Professor at Tu Delft Abstract: Machine learning usually requires large amounts of data to work well. But how much data is exactly required for sufficient performance? This can be estimated using learning curves. Learning curves plot a machine learning model’s performance versus the amount of data it is trained on. Note: the… Read more: Learning Curve Extrapolation with PFN’s

Jiarong Pan PhD at Bosch Center for Artificial Intelligence Abstract: Many real-world applications consider multiple objectives, potentially competing ones. For instance, for a model deciding whether to grant or deny loans, ensuring accurate while fair decisions is critical. Multi-objective Bayesian optimization (MOBO) is a sample-efficient technique for optimizing an expensive black-box function across multiple objectives.… Read more: Meta-learning for scalable multi-objective Bayesian optimization

Annelot Bosman PhD at Universiteit Leiden This project aims to investigate fairness from a new perspect- ive, namely by using robustness distributions, introduced in previous work. Investig- ating robustness in neural networks is very computationally expensive and as such the community has directed focus on increasing verification speed. Robustness distributions, although expensive to obtain, have… Read more: Using robustness distributions to better understand fairness in Neural Net-works

Peter Pavlík PhD student at slovak.AI Abstract: Nowcasting in meteorology is defined as forecasting with high local detail, by any method, over a period from the present to six hours ahead. In general, the main nowcasting task is to predict precipitation amounts in the near future and generate alerts on extreme weather events, preventing damage… Read more: Evaluating the Effect of Additional Data Channels for CNN-based Radar Precipitation Nowcasting

Dulce Canha PhD student at Luxembourg Institute of Health (LIH) Abstract: Type-1 diabetes (T1D) is an autoimmune disorder representing 5-10% of global diabetes cases, with a predicted patient growth from 8.4 million in 2021 to potentially 17.4 million by 2040. This chronic disease requires complex daily management, making people with T1D more prone to psychological… Read more: Development of a neuro-symbolic AI approach to characterize diabetes distress profiles in people with type-1 diabetes

Peter Anthony PhD student at Slovak.AI Comenius University in Bratislava, Slovakia Abstract: Malware detection is a critical task in cybersecurity, and traditional signature-based approaches are often ineffective against new and evolving threats. Recent research has shown that machine learning models can improve the accuracy of malware classification. However, existing methods often suffer from poor generalization… Read more: Malware Detection Based on Explainable AI

Abir Elbeji Luxembourg Institute of Health (LIH) Abstract: Depression affects around 4.4% of the global population, requiring early and accurate screening to reduce its long-term damage. Traditional screening approaches such as self-reported questionnaires have limitations, prompting the shift to objective assessment methods such as voice-based biomarkers. These biomarkers offer non-invasive and scalable depression screening, though… Read more: Multitask learning for enhanced depressive symptoms screening using real-life voice recordings

Matthias könig PhD at Leiden University Abstract: This project seeks to advance the state of the art in formal neural network verification. Formal neural network verification methods check whether a trained neural network, for example an image classifier, satisfies certain properties or guarantees regarding its behaviour, such as correctness, robustness, or safety, under various inputs… Read more: Improving inverse abstraction based neural network verification using automated machine learning techniques

Branislav Pecher PhD at Kempelen Institute of Intelligent Technologies, member of Slovak.AI Abstract: Learning with limited labelled data, such as meta-learning, transfer learning or in-context learning, aims to effectively train a model using only a small amount of labelled samples. However, there is still limited understanding of the required settings or characteristics for these approaches… Read more: Towards Stable and Robust Learning with Limited Labelled Data: Investigating the Impact of Data Choice

Ya Song PhD student at Eindhoven University of Technology Abstract: In the research field of solving combinatorial optimization problems, many studies have considered combining machine learning with optimization algorithms and proposed so-called learning-based optimization algorithms. Compared to traditional handcrafted algorithms, these methods can automatically extract relevant knowledge from training data and require less domain knowledge. In… Read more: Graph Representation Learning for Solving Combinatorial Optimization Problems

Martina cinquini PhD student at the University of Pisa Abstract: Artificial Intelligence (AI) has become ubiquitous in many sensitive domains where individuals and society can potentially be harmed by its outputs. In an attempt to reduce the ethical or legal implications of AI-based decisions, the scientific community’s interest in fairness-aware Machine Learning has been increasingly… Read more: Causal Analysis for Fairness of AI Models

Martina Bacaro PhD student at the University of Bologna – Alma Mater Studiorum Abstract: Interactions between humans and robots are increasing both in specialistic and everyday scenarios. Trustworthiness is acknowledged as a key factor for successful engagements between humans and robots. For humans to understand and rely on robots’ actions and intentions, they need to… Read more: How we trust robots: Attribution of Intentionality, Anthropomorphism and Uncanny Valley Effect