I will discuss reliability of Machine Learning (ML) algorithms, from the perspective of adversarial learning and its implications in terms of model quality and robustness given new data. The talk will highlight how adversarial learning can be used as a valuable tool...

Uniformly distributed point sets of low discrepancy are heavily used in experimental design and across a very wide range of applications such as numerical integration, computer graphics, and finance. Recent methods based on Graph Neural Networks [Rusch et al., PNAS...

Panoptic segmentation provides a comprehensive understanding of visual scenes by assigning each pixel a semantic class label and, for objects, an instance ID. While highly effective, traditional methods rely heavily on large-scale annotated datasets, posing...

Automated machine learning has been successful in supporting data scientists in selecting appropriate machine learning architectures, as well as optimizing hyperparameters. By doing so…

Metaheuristics, such as evolutionary algorithms, ant colony optimization, and particle swarm optimization, are among the most successful techniques for solving complex optimization problems. Historically, the design of metaheuristic algorithms…

Why do patterns emerge in nature, and what do they reveal about underlying processes? From the stripes on a zebra to waves in the ocean, patterns offer insight into complex systems. In our study, we explore…

Machine learning (ML) models depend on the data on which they are trained. Consequently, flaws in datasets can lead to significant vulnerabilities in ML models …

Why do societies collapse? Some famous examples include Easter Island, the Maya, the Roman Empire, and the Chinese dynasties. The speaker has developed mathematical models for these historical cases and the talk will focus on…