About
The AI@JSI seminars are a series of events focused on Artificial Intelligence, hosted by the Department of Knowledge Technologies at the Jožef Stefan Institute. About once a month, we invite researchers from around the world to present their work, aiming to inform both the professional community and the general public about the latest advancements in this field. Below, you will find information on the upcoming event, as well as details and recordings of past events.
Below, you can subscribe to the AI@JSI Seminar mailing list.
Upcoming event
Past events
Many real-world systems—from physiology and neuroscience to climate and finance—are inherently non-stationary, operating far from equilibrium with structure that evolves in time. This talk presents a physical and data-driven framework for understanding such systems...
Cross-modal knowledge distillation (CMKD) refers to the scenario in which a learning framework must handle training and test data that exhibit a modality mismatch, more precisely, training and test data do not cover the same set of data modalities. Traditional...
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...
Self-organisation sculpts the topology and physicochemical properties of biological, organic, inorganic, and hybrid materials. Its explainability emerges from understanding the core principles and preconditions that dictate synthetic outcomes. A formal,...
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 …
