AI@JSI | Department of Knowledge Technologies

AI-enabled Mammography

Anja Glusic — Thu, 05 Mar 2026 12:18:05 +0000

Breast cancer is the most common malignancy and leading cause of cancer deaths in women around the world. The preferred diagnostic and prevention method used to fight breast cancer is mammography, being effective, cheap, reliable and suitable for screening large populations. The analysis of mammograms requires considerable effort from qualified radiologists, who have been increasingly relying on computer-aided diagnosis and the development of tools that require little supervision could save the lives of hundreds of thousands of women across the world.

In recent years, the integration of Artificial Intelligence (AI) in the field of medicine has brought about a significant transformation in healthcare delivery. Computer vision technology finds itself at the forefront of this proces. Its applications to mamography data represent an active research field, stimulated by the fact that among the clinical imaging modalities, mammography stands out in terms of high spatial resolution (full-field digital mammography systems usually produce images at resolutions ranging from 1920×2304 to 4708×5844 pixels.

I will discuss research work stemming from projects conducted at the Institute for Artificial Intelligence Research and Development of Serbia, aimed at implementing AI-assisted mamography screening at the national level. Viewed through the lens of medical applications, the talk will cover the evolution of state-of-the-art research in the domain of computer vision and multimodal AI over the last 5 years, from the applications of “classical” convolutional neural networks and visual transformer models, explainable AI extensions, generative (diffusion) models, to self supervised and multiple instance learning approaches to address specific challenges and (downstream) tasks such as: image classification, lesion detection and synthetic mammogram generation.

Zoom link: Click me. (Audio issues from last time are being actively addressed.)

Learning Non-Stationary Dynamics: Oscillations, Chronotaxicity, and Time-Varying Structure in Complex Systems

Nina Omejc — Mon, 26 Jan 2026 10:09:48 +0000

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 through time-varying oscillatory dynamics. Central to this approach is the concept of chronotaxic systems: non-autonomous oscillators with dynamically stable, time-dependent characteristic frequencies, providing a principled way to model robustness and adaptability without assuming stationarity or time-asymptotic behaviour.

I will discuss how instantaneous frequency, nonlinear mode decomposition, and multiscale ridge extraction enable the learning of interpretable latent dynamics from complex, noisy time series where classical spectral methods fail. These methods form the basis of the MODA toolbox and support reliable separation, tracking, and interpretation of interacting components with evolving amplitudes and frequencies.

The framework further enables inference of time-varying interactions and causal structure using wavelet-based coherence, information-theoretic measures, and Bayesian dynamical inference, including in networks with non-stationary coupling. Applications will be drawn primarily from physiology and neuroscience—such as neurovascular coupling, anaesthesia-induced phase transitions, and ageing—but the methods generalise across domains, including physical, engineered, and socio-economic systems.

The talk highlights how physically grounded models of non-stationary dynamics complement machine learning by providing interpretable representations, principled constraints, and reliable inference in settings where purely data-driven approaches struggle.

Zoom link: Click me.

Reliable Machine Learning – Methods and Applications in Environmental Sciences

Anja Glusic — Thu, 22 May 2025 14:20:56 +0000

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 to measure and improve reliability, particularly in the domain of environmental sciences.
Highlighting the central role of reliable ML in environmental sciences, I will showcase our work in various applications in environmental sciences, particularly atmospheric and environmental chemistry.

For an overview of my ongoing research projects visit my lab’s webpage at: https://wickerlab.org.

Address of the Zoom meeting: https://zoom.us/j/93704860483?pwd=6XAVHx5guys9a94XTNlUaXkHTozdbl.1

Generating Point Sets of Small Star Discrepancy

Anja Glusic — Fri, 07 Mar 2025 07:59:00 +0000

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 2024] and solver-based optimization [Clément et al., accepted in Proceedings of the AMS] identified point sets having much lower discrepancy than previously known constructions. We show that further substantial improvements are possible by separating the construction of low-discrepancy point sets into (i) the relative position of the points, and (ii) the optimal placement respecting these relationships. Using tailored permutations, we construct point sets that are of 20\% smaller discrepancy on average than those proposed by Rusch et al. In terms of inverse discrepancy, our sets reduce the number of points in dimension 2 needed to obtain a discrepancy of 0.005 from more than 500 points to less than 350. For applications where the sets are used to query time-consuming models, this is a significant reduction.
The presentation is based on joint work with François Clément (University of Washington, US), Kathrin Klamroth (University of Wuppertal, Germany), and Luís Paquete (University of Coimbra, Portugal).

Label-efficient panoptic segmentation

Anja Glusic — Tue, 14 Jan 2025 15:10:23 +0000

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 significant challenges for scalability and adaptability. Additionally, the process of annotating images with panoptic labels is both labor-intensive and time-consuming, highlighting the importance of label-efficient approaches. In this talk, I will present an overview of various label-efficient methods, focusing on my recent work in unsupervised domain adaptation and semi-supervised learning. I will also discuss the emerging field of open-vocabulary panoptic segmentation, which extends recognition capabilities to categories beyond the training taxonomy.

Zoom link:
https://zoom.us/j/95847029023?pwd=hYqMPhZ4K2yVttbCl5gSCDvYNIGBZN.1

Multi-Objective AutoML: Towards Accurate and Robust Neural Networks

Anja Glusic — Mon, 02 Dec 2024 13:31:45 +0000

Automated machine learning has been successful in supporting data scientists in selecting appropriate machine learning architectures, as well as optimizing hyperparameters. By doing so, data scientists can focus their attention on more important tasks. Partially thanks to the TAILOR project, in which Leiden University and JSI have successfully collaborated, we have seen a demand on AutoML techniques to not only provide solutions that are accurate, but also those that are trustworthy according to several relevant criteria. In particular neural networks are known to be vulnerable to adversarial attacks, whereas robustness (against such attacks) is an important criterion of trustworthiness. In this talk, I will summarize various projects we have done through this collaboration, that envision AutoML solutions that specifically address robustness of neural networks.

Zoom link:
https://zoom.us/j/91879263877?pwd=9sxadIBnOrSxnyZdipwLiNNurcta3O.1

Designing New Metaheuristics: Manual Versus Automatic Approaches

Anja Glusic — Tue, 19 Nov 2024 08:26:08 +0000

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 has been a manual process, guided by the experience and intuition of the algorithm designers, who often spend an excessive amount of time and effort trying to find designs that perform well for the optimization problem at hand.

In this talk, after discussing the drawbacks of manually designing metaheuristic algorithms, I will elaborate on some of the unintended negative consequences that the initially successful approach of “looking to nature for inspiration” has brought to the field of optimization. I will then describe the basics of the automatic design approach, which is an efficient alternative to manual design that allows the creation of high-performance implementations without the need for human intervention. Finally, I will present METAFOR, a metaheuristics software specifically developed for the automatic design of hybrid metaheuristics that has been shown to be capable of automatically generating metaheuristic algorithms that outperform the state of the art.

Modeling Rac1 Dynamics: Insights into Cellular Movement and Internal Mechanics

Anja Glusic — Fri, 08 Nov 2024 10:20:31 +0000

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 how single-celled amoebae generate dynamic patterns of a protein called Rac1, which controls cell movement. Through mathematical modeling and experiments, we analyze how Rac1 switches on and off along the cell membrane to create waves and oscillations. These patterns not only help us understand how cells navigate their environment but also reveal the internal reaction networks that drive cellular behavior.
This talk will introduce the basics of cell motility, our modeling methods, and the role of randomness, or “noise,” in pattern formation. We’ll also look ahead to future work involving a systematic search through model space using equation discovery methods.

Zoom link: https://us04web.zoom.us/j/79055582790?pwd=zuc3RsogHj0Gex43ilMEx8TOiETGxp.1

ML Model Reliability From a Dataset Perspective

Anja Glusic — Fri, 18 Oct 2024 12:31:30 +0000

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. ML practitioners frequently tend to focus on “correcting” the model without addressing the quality of the dataset. However, recognizing dataset flaws early can inform and guide subsequent data collection and improve the dataset’s overall quality. In my talk, I will advocate for this data-centric perspective. I will present my research in related areas, including selection bias identification and mitigation, applicability domains, adversarial learning, self-reinforcing bias, and active learning.

Modelling the collapse of complex societies

Anja Glusic — Thu, 26 Sep 2024 13:00:03 +0000

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 the general lessons that can be learned from them. The main topics covered include a historical background on collapse, the role of complexity and feedback mechanisms, the modelling methodology and criteria, how time scales matter, why networks of societies can be more sustainable and if time permits will discuss some implications for modern society.