Differences
This shows you the differences between two versions of the page.
| Both sides previous revisionPrevious revisionNext revision | Previous revision | ||
| aira:start [2025/12/03 10:45] – [Schedule Autumn 2025] mtm | aira:start [2026/01/30 11:04] (current) – [Schedule Autumn 2025] mtm | ||
|---|---|---|---|
| Line 22: | Line 22: | ||
| ===== Schedule Autumn 2025 ===== | ===== Schedule Autumn 2025 ===== | ||
| - | * **[PHD TRACK] | + | * **[PHD TRACK] |
| - | * Meeting link: TDA | + | * Meeting link:[[https:// |
| - | * Recording: | + | * Recording: |
| + | * Presentation slides: | ||
| + | |||
| + | * **[PHD TRACK] 2026.01.22**: | ||
| + | * Meeting link: | ||
| + | * Recording: [[https:// | ||
| + | * Presentation slides: | ||
| + | |||
| + | * **[RESEARCH TRACK] 2026.01.15**: | ||
| + | * Meeting link: | ||
| + | * Recording: | ||
| * Presentation slides: | * Presentation slides: | ||
| + | |||
| + | * **[PHD TRACK] 2026.01.08**: | ||
| + | * Meeting link: | ||
| + | * Recording: | ||
| + | * Presentation slides: | ||
| + | |||
| + | * **[RESEARCH TRACK] 2025.12.18**: | ||
| + | * Meeting link: | ||
| + | * Recording: | ||
| + | * Presentation slides: | ||
| + | |||
| + | * **[PHD TRACK] 2025.12.11**: | ||
| + | * Meeting link: [[https:// | ||
| + | * Recording: [[https:// | ||
| + | * Presentation slides: {{: | ||
| + | |||
| + | * **[PHD TRACK] 2025.12.04**: | ||
| + | * Meeting link: [[https:// | ||
| + | * Recording: | ||
| + | * Presentation slides: | ||
| * **[RESEARCH TRACK] 2025.11.27**: | * **[RESEARCH TRACK] 2025.11.27**: | ||
| Line 35: | Line 65: | ||
| * Meeting link: | * Meeting link: | ||
| * Recording - Barbara Moreová: | * Recording - Barbara Moreová: | ||
| - | * Recording - Mateusz Ploskonka: | ||
| - | * Recording - Kateřina Hrudková: | ||
| * Presentation slides - Barbara Moreová: | * Presentation slides - Barbara Moreová: | ||
| + | * Recording - Mateusz Ploskonka: | ||
| * Presentation slides - Mateusz Ploskonka: | * Presentation slides - Mateusz Ploskonka: | ||
| + | * Recording - Kateřina Hrudková: | ||
| * Presentation slides - Kateřina Hrudková: | * Presentation slides - Kateřina Hrudková: | ||
| Line 44: | Line 74: | ||
| * Meeting link: | * Meeting link: | ||
| * Recording - Tomáš Kliegr: | * Recording - Tomáš Kliegr: | ||
| - | * Recording - Lukáš Sýkora: | ||
| * Presentation slides - Tomáš Kliegr: | * Presentation slides - Tomáš Kliegr: | ||
| + | * Recording - Lukáš Sýkora: | ||
| * Presentation slides - Lukáš Sýkora: | * Presentation slides - Lukáš Sýkora: | ||
| Line 491: | Line 521: | ||
| + | |||
| + | ==== 2026-01-29 ==== | ||
| + | <WRAP column 15%> | ||
| + | {{ : | ||
| + | </ | ||
| + | |||
| + | <WRAP column 75%> | ||
| + | |||
| + | **Speaker**: | ||
| + | |||
| + | **Title**: Calm-Data Generator: A Flexible Framework for Synthetic Dataset Creation Under Concept Drift. | ||
| + | |||
| + | **Abstract**: | ||
| + | Calm-Data Generator is designed to produce realistic synthetic datasets exhibiting different types of concept drift, enabling controlled evaluation of machine-learning models in dynamic environments. The framework implements multiple drift mechanisms, supports tabular data with customizable complexity, and provides a flexible API for defining data-generation functions, experimental scenarios, and temporal transitions. Its primary goal is to facilitate reproducible experimentation in concept drift research, allowing researchers to benchmark methods, analyze performance degradation, | ||
| + | |||
| + | **Biogram**: | ||
| + | Antonio Guillén-Teruel (a.guillenteruel@um.es) is a PhD Student graduated in Mathematics from the University of Murcia in 2020. In 2021 he got a Masters degree in Big Data from the same university and started his Ph.D studies in Informatics. The following year he got a Masters degree in Advanced Mathematics at the University of Murcia. His research focuses on imbalanced problems in Machine Learning (ML), including both in regression and classification problems, as well as the study of concept drift in medical domains for imbalanced datasets. | ||
| + | </ | ||
| + | <WRAP clear></ | ||
| + | |||
| + | ==== 2026-01-22 ==== | ||
| + | <WRAP column 15%> | ||
| + | {{ : | ||
| + | </ | ||
| + | |||
| + | <WRAP column 75%> | ||
| + | |||
| + | **Speaker**: | ||
| + | |||
| + | **Title**: Localizing the invisible: Graph Neural Networks for Biomedical Signals. | ||
| + | |||
| + | **Abstract**: | ||
| + | The respiratory system can be significantly affected by thoracic injuries, which may lead to complications such as lung dysfunction. Immediate diagnosis, along with the precise location of these injuries is crucial as it allows targeted medical interventions, | ||
| + | This talk introduces a wearable sensor network coupled with Temporal Graph Neural Networks (TGCNs) to detect and localize breathing abnormalities non-invasively and in real time. By modeling the thorax as a graph of 14 IMU-based sensor nodes, the system captures both spatial dependencies and temporal dynamics of chest movement. The proposed model pinpoints the exact location and severity of breathing irregularities, | ||
| + | The presentation will cover the underlying method, synthetic to real data strategy and the vision of a smart chest wearable system for continuous at home monitoring. Applications range from post-injury recovery and chronic disease management to early warning systems in preventive healthcare. | ||
| + | |||
| + | **Biogram**: | ||
| + | Zaidi is a PhD researcher at Otto-von-Guericke University Magdeburg, working at the Knowledge Management & Discovery Lab (KMD) under the supervision of Prof. Myra Spiliopoulou. His research focuses on graph neural networks, wearable sensor systems and feature importance for biomedical applications. | ||
| + | He has developed a temporal graph neural network framework to detect and localize respiratory abnormalities using chest-mounted IMU sensor networks. Beyond respiratory monitoring, his research spans spatio-temporal deep learning, health signal processing and interpretable machine learning methods aimed at bridging the gap between AI research and clinical practice. | ||
| + | |||
| + | </ | ||
| + | <WRAP clear></ | ||
| + | |||
| + | ==== 2026-01-15 ==== | ||
| + | <WRAP column 15%> | ||
| + | {{ : | ||
| + | </ | ||
| + | |||
| + | <WRAP column 75%> | ||
| + | |||
| + | **Speaker**: | ||
| + | |||
| + | **Title**: Knowledge Graphs and Polyvocality in Cultural Heritage and Beyond. | ||
| + | |||
| + | **Abstract**: | ||
| + | Over the past decade, Knowledge Graphs (KGs) have emerged as one of the most promising technologies for organizing and exploring cultural heritage data. Within this domain, several international standards have been developed to enable interoperable modelling of library, archive, and museum resources, such as CIDOC-CRM and LRMoo. Alongside these standards, new conceptual and methodological trends—such as polyvocality representation—are reshaping how cultural narratives and multiple perspectives can be expressed, connected, and contextualized within KGs. In this talk, I will share insights from my experience developing and applying KGs in two cultural heritage–related projects: CHExRISH and LKG. I will also discuss ongoing and future work on polyvocality in and beyond cultural heritage domains. | ||
| + | |||
| + | **Biogram**: | ||
| + | Luiz do Valle Miranda is a Ph.D. candidate at the Jagiellonian University in Technical Computer Science since 2023. He graduated in BA in Cognitive Science at the John Paul II Catholic University of Lublin (2018), received the title of MA in Philosophy from the University of Antwerp (2020) and has a Ph.D. in Philosophy from the Charles University in Prague (2024). | ||
| + | His research focuses on the development of knowledge-based systems, with particular emphasis on knowledge graphs. He is especially interested in the intersection of language model applications and explicitly represented knowledge, aiming to create intelligent technologies that promote human diversity and flourishing. | ||
| + | </ | ||
| + | <WRAP clear></ | ||
| + | |||
| + | ==== 2026-01-08 ==== | ||
| + | <WRAP column 15%> | ||
| + | {{ : | ||
| + | </ | ||
| + | |||
| + | <WRAP column 75%> | ||
| + | |||
| + | **Speaker**: | ||
| + | |||
| + | **Title**: Counterfactual Guidance for Transparent Hyperparameter Tuning. | ||
| + | |||
| + | **Abstract**: | ||
| + | This research explores how hyperparameter optimization can be made more transparent and interactive by incorporating human preferences into the search process. Instead of treating optimization as a black-box task, the approach uses counterfactual explanations to suggest alternative configurations under user-defined constraints. The method enables domain experts to better understand and guide model behavior, supporting more informed decision-making. | ||
| + | |||
| + | **Biogram**: | ||
| + | Sabri Manai is a PhD candidate in Technical Computer Science at Jagiellonian University in Kraków, where his research focuses on explainable AI and pattern detection in multimodal data. His work investigates how human feedback and domain knowledge can improve the transparency and reliability of AI systems. | ||
| + | He holds a Master’s degree in Software Systems Engineering from the Universitat Politècnica de València and a Bachelor’s degree in Computer Science from the South Mediterranean University in Tunis. Previously, he worked on AI-driven urban analytics within the Valencia Smart City project at Idrica and contributed to mobile development and cloud integration at Peaksource. | ||
| + | </ | ||
| + | <WRAP clear></ | ||
| + | |||
| + | ==== 2025-12-18 ==== | ||
| + | <WRAP column 15%> | ||
| + | {{ : | ||
| + | </ | ||
| + | |||
| + | <WRAP column 75%> | ||
| + | |||
| + | **Speaker**: | ||
| + | |||
| + | **Title**: Normalizing Flows - fundamental concepts and applications in counterfactual explanations. | ||
| + | |||
| + | **Abstract**: | ||
| + | During the talk, I will begin with a brief introduction to generative flow-based models. Then, I will present practical examples demonstrating how this class of models can be applied in real-world scenarios. I will introduce flows as probabilistic regression models, highlighting their versatility as plug-in components and their generative capabilities for point clouds. I will also discuss how we applied flow-based models to a few-shot regression problem. Finally, I will illustrate how normalizing flows can be used to address counterfactual explanation tasks. | ||
| + | |||
| + | **Biogram**: | ||
| + | Maciej Zięba is a research scientist at Tooploox and an Associate Professor at Wroclaw University of Science and Technology, where he received a Ph.D. degree in computer science and a master' | ||
| + | |||
| + | </ | ||
| + | <WRAP clear></ | ||
| + | |||
| + | |||
| + | ==== 2025-12-11 ==== | ||
| + | <WRAP column 15%> | ||
| + | {{ : | ||
| + | </ | ||
| + | |||
| + | <WRAP column 75%> | ||
| + | |||
| + | **Speaker**: | ||
| + | |||
| + | **Title**: Enhancing Knowledge Engineering with LLMs. | ||
| + | |||
| + | **Abstract**: | ||
| + | The development and spread of Large Language Models (LLMs) are having a growing impact on the world of the Semantic Web, profoundly transforming the field of Knowledge Engineering. This field, traditionally characterized by a high degree of manual work and collaboration between technical professionals and domain experts, faces various challenges related to scalability and the continuous evolution of knowledge. In this context, LLMs are emerging in several areas, from law to medicine, as tools that support researchers: | ||
| + | |||
| + | **Biogram**: | ||
| + | Anna Sofia Lippolis (she/her) is a PhD student at the University of Bologna, Italy, affiliated with the National Research Council’s Institute for Cognitive Sciences and Technologies (Rome, Italy). Her work investigates how semantic technologies intersect with Digital Humanities research and how AI can automate knowledge-engineering practices. | ||
| + | |||
| + | </ | ||
| + | <WRAP clear></ | ||
| ==== 2025-12-04 ==== | ==== 2025-12-04 ==== | ||
| Line 505: | Line 658: | ||
| **Abstract**: | **Abstract**: | ||
| One branch of systematic trading research studies large libraries of formulaic alphas: small predictive models built from price and volume data. In practice, these alphas are combined into an ensemble whose composition changes with market conditions. From an ML perspective, | One branch of systematic trading research studies large libraries of formulaic alphas: small predictive models built from price and volume data. In practice, these alphas are combined into an ensemble whose composition changes with market conditions. From an ML perspective, | ||
| - | In this talk I will introduce this setting with minimal financial background (cross-sectional returns, information coefficient, | + | In this talk I will introduce this setting with minimal financial background (cross-sectional returns, information coefficient, |
| **Biogram**: | **Biogram**: | ||
