Department of Applied Informatics - Comenius University in Bratislava

gratulujeme! 👏

✨náš kolega Ján Kľuka získal prvé miesto v súťaži o najlepšiu publikáciu na fakulte nášho Pražského partnera v kategórii žurnálový článok! 🏆 Gratulujeme! ✨

Prečítajte si ho tu 👇

https://content.iospress.com/articles/semantic-web/sw233401

Viac informácií tu:https://fis.vse.cz/wp-content/uploads/page/266/2024_Cena-dekana_NEJLEPSI-PUBLIKACE-2023.pdf

Focused categorization power of ontologies: General framework and study on simple existential concept expressions - IOS Press When reusing existing ontologies for publishing a dataset in RDF (or developing a new ontology), preference may be given to those providing extensive subcategorization for important classes (denoted as focus classes). The subcategories may consist no

In mid-May, the TERAIS team from DAI UKBA took an active part in the 22nd Conference on Cognition and Artificial Life in Olomouc. This international conference provides a platform for presenting the latest research in various fields of cognitive science, encompassing both living and artificial systems🧠

As part of the future improvements we would like to know opinions from past, present or potential conference participants.

Please share your thoughts by completing this short, anonymous survey 👇

If you would like to read about our participation click here 👉 https://terais.eu/post/24-06-10-cal-conference/

Quo vadis, Kognícia a umelý život? / Cognition and artificial life - conference preferences survey Milí tradiční, noví alebo potenciálni účastníci a účastníčky česko-slovenskej konferencie Kognícia a umelý život (KUŽ), radi by sme zistili vaše preferencie. Konferencia má viac ako 20-ročnú tradíciu, ale chceli by sme, aby bola moderná a zodpovedala vaším potrebám. Dajte n...

Vedec roka Igor Farkaš: Neurónová sieť rozpozná tvár či objekt, no nemusí im rozumieť Profesor Igor Farkaš z Katedry aplikovanej informatiky FMFI UK získal ocenenie Vedec roka SR 2023 v kategórii Osobnosť medzinárodnej spolupráce za významné výsledky v oblasti umelej inteligencie, za...

✨ We are excited to kick off the MEi:CogSci Conference 2024 starting today at DAI UKBA! ✨

Join us for three days of groundbreaking research, engaging discussions, and unparalleled networking opportunities in the field of cognitive science 🧠

Check out the schedule and all the details about the conference here 👇

Proceedings of the MEi:CogSci Conference Proceedings of the Middle European Interdisciplinary Master in Cognitive Science Conference

this week we have been hosting international students within the Trustworthy Human-Robot Interaction Summer School as part of TERAIS project 🤖

Check all the information on summer school here 👇

Trustworthy Human-Robot Interaction Summer School | TERAIS Introduction Timetable THRISS Venue About THRISS Organizing Committee Invited Speakers and Lecturers Lectures Workshops Student Enrollment Introduction The Trustworthy Human-Robot Interaction Summer School or THRISS welcomes participants from different backgrounds to meet for four days and deepen th...

Pozrite si nášho kolegu Martina Takáča, ktorý vystúpil v televíznej debate na tému Riziká umelej inteligencie v relácii Cez lupu na RTVS:24

Cez lupu Kauzy, kriminálne prípady, životné situácie, udalosti. Témy, o ktorých je dobré vedieť viac.

gratulujeme v mene celej katedry 🙂

Profesor Igor Farkaš z Fakulty Matematiky, fyziky a informatiky UK získal ocenenie Vedec roka za významné vedecké výsledky v oblasti umelej inteligencie s využitím modelov umelých neurónových sietí, získané v spolupráci so zahraničnými partnermi, a za rozvíjanie medzinárodného interdisciplinárneho magisterského programu kognitívna veda https://fmph.uniba.sk/detail-novinky/back_to_page/fakulta-matematiky-fyziky-a-informatiky-uk/article/vedcom-roka-za-rok-2023-v-kategorii-osobnost-medzinarodnej-spoluprace-je-profesor-igor-farkas/

vypočujte si podcast s našim kolegom Viktorom Kocurom 👇

PODCAST: Ako nás vidia počítače? - VEDA NA DOSAH S informatikom Viktorom Kocurom sme sa rozprávali o pokročilých modeloch a trendoch v oblasti počítačového videnia.

✨Another week we are starting with the doctoral colloquium✨

Zekeri Adams with the topic Reasoning in higher order description logics towards meta modelling ontology design patterns

Abstract: Integrating higher-order description logic (DLs) with meta-modeling techniques has emerged as a promising approach for enhancing the design and development of ontology-based systems. By leveraging the expressive power of higher-order logic, practitioners can capture complex relationships and dependencies within ontological models, enabling more precise and comprehensive representations of domain knowledge. Furthermore, the use of meta-modeling techniques, including conceptual-oriented and description logic approaches, facilitates the systematic organization and reuse of ontology design patterns across different domains and applications.
In this presentation, we explore the conceptual meta-modeling ontology design patterns using the PURO language in relation to MLT. Through the utilization of the PURO Modeler tool, we demonstrate the practical significance of this language, employing segments from the well-known knowledge graph, Wikidata, as illustrative examples. Additionally, we delve into the current state-of-the-art in description logic (DLs) meta-modeling ontology design patterns and discuss future directions in this design pattern space.

More about all colloquia here 👉https://dai.fmph.uniba.sk/w/Doctoral_Colloquia/en

✨Exciting opportunity alert✨

We are on a lookout for two talented postdoctoral researchers to join DAI under the Horizon Europe TERAIS project 🤖

For further details about the click here 👇 and submit your

https://euraxess.ec.europa.eu/jobs/234277



For more about TERAIS project 👉https://terais.eu/

Looking for 2 Post docs for TERAIS project Comenius University Bratislava is looking for two excellent postdoctoral researchers to work on a Horizon Europe twinning project: TERAIS - Towards Excellent Robotics and Artificial Intelligence at a Slovak university.

Our colleague Igor Farkas participated at NET2 workshop meeting within the TRAIL project - Transparent Interpretable Robots in Barcelona

Doctoral researchers got the opportunity to showcase their cutting-edge research and delve into fascinating discussions on transparent and interpretable robots🤖



More about TRAIL Project 👉https://www.inf.uni-hamburg.de/research/projects/trail.html

✨Another week we are starting with the doctoral colloquium✨

Ján Pastorek with the topic Partial automorphisms and asymmetry level of graphs

Abstract: Graphs consisting of nodes interconnected by links can express underlying structure of many things we encounter. These graphs frequently exhibit "asymmetric" features but also various kinds of "symmetry". What is the relation between "symmetry" and "asymmetry" of graphs?
Understanding the complex relationships among asymmetric graphs, regular graphs, and graphs with non-trivial automorphisms is challenging. The majority of graphs are well-known to be asymmetric, i.e., having no non-trivial automorphisms. Interestingly, almost all regular graphs, where all "highly-symmetric graphs" concentrate, have only trivial automorphisms, with the Frucht graph being one of the smallest. Notably, removing a single vertex from a graphical regular representation, which captures one of the notions of symmetry, can yield an asymmetric graph. On the other hand, there exist minimal asymmetric graphs where each vertex-induced subgraph possesses non-trivial automorphisms. But already any two-vertex induced subgraph in a graph has non-trivial automorphism.
These findings highlight the importance of partial automorphisms, which are isomorphisms between two induced subgraphs of a graph. Our research delves into the properties of the partial automorphisms of graphs, focusing on the measure of (a)symmetry of a graph, defined as the ratio of the largest rank of a non-trivial partial automorphism to the graph's order. In our presentation, we will discuss computational and theoretical insights from our research in this area.

More about all colloquia here 👉https://dai.fmph.uniba.sk/w/Doctoral_Colloquia/en

✨Another week we are starting with the doctoral colloquium✨

Radovan Gregor with the topic Mirroring mechanisms for trustworthy human-robot interaction

Abstract: The discovery of a group of neurons in the premotor cortex of macaque monkeys that became active both when the monkeys performed certain actions and when they observed another individual performing the same actions proposed the existence of a neural system that "mirrors" the actions of others, giving rise to a name Mirror Neuron System (Rizzolatti G., 1992). This discovery has had a major impact on our understanding of the neural basis of social cognition and has been the subject of numerous studies. This presentation will investigate the use of mirroring mechanisms for establishing trustworthy human-robot interaction. Specifically, it will focus on designing a MNS model based on neural networks, implementing it in a humanoid robot NICO and evaluating its effectiveness in human-robot interaction scenarios.

More about all colloquia here 👉https://dai.fmph.uniba.sk/w/Doctoral_Colloquia/en

✨Exciting Opportunity Alert! ✨

Are you passionate about advancing research in , computer science and computer engineering with a focus on ? Check out this amazing opportunity to join a dynamic team as a Doctoral Researcher at DAI!

Don't miss out on this chance to take your career to new heights! Apply now!📄

For all the information click here 👉https://euraxess.ec.europa.eu/jobs/229162

Open call: Doctoral Researcher Comenius University Bratislava is looking for an excellent doctoral researcher to work on a Horizon Europe MSCA project: TRAIL – TRAnsparent InterpretabLe robots.

✨Another week we are starting with the doctoral colloquium✨

Elena Štefancová with the topic Fairness-aware Recommender Systems

Abstract: Overview of recommender systems and their issues with focus on fairness challenges which often have a complexity in practice that is not adequately captured in simplified research formulations.

More about all colloquia here 👉https://dai.fmph.uniba.sk/w/Doctoral_Colloquia/en

Thrilled to share that we recently welcomed students from FH Technikum Wien in our labs! 🎉 They had the chance to meet NICO 🤖 and learn about our in , , and through our project.

Dive into the details about TERAIS project 👉 http://terais.eu

✨Another week we are starting with the doctoral colloquium✨

Fatana Jafari with the topic Classification and Detection of Multiple Sclerosis White Matter Lesions in Brain MR Images Using Deep Learning and Explainable AI Methods

Abstract: Multiple sclerosis (MS) white matter lesions in brain is an immunological illness affecting the central nervous system of the body. This condition causes damaging symptoms to the body, such as blurred eyesight, pain, exhaustion and imbalanced muscles. The physical effects of multiple sclerosis in brain have caused people to lose their ability to function in daily life. So, early diagnosis is the sole action that we can do to prevent MS from progressing. Many researches have already done to detect MS in brain using DL and ML algorithms. However, the decision-making processes within these systems often resemble "black boxes," where the logic and reasoning behind their outputs remain ambiguous for the end-users. This lack of transparency raises significant practical concerns. That is why, In this research we propose an interpretable Multiple sclerosis white matter lesion classification and diagnostic system using DL model and MRI datasets. The primary goal of our research project is not only classification and precise diagnosis with high accuracy of MS in brain, but also its explainability. We aim to integrate two most popular XAI approaches with DL model such as SHAP (SHapley Additive Explanations) values and LIME (Local Interpretable Model Agnostic Explanations ) to provide explanations for the predictions provided by Blackbox models. As a result these approaches increases the confidence and trustworthy in the black-box model’s decision to be employed in crucial applications under the supervision of human specialists.

More about all colloquia here 👉https://dai.fmph.uniba.sk/w/Doctoral_Colloquia/en

Last week we had a visit from Estonia from Tartu Ülikool !🤖

Grateful for the opportunity to share insights into our robotics and cognitive science research projects here at DAI. Looking forward to potential collaborations in the future! 🤝

📢 už tento štvrtok, 18. 4., sa na našej fakulte uskutoční Študentská vedecká konferencia! 84 talentovaných študentov a študentiek predstavia svoje prvotné vedecké objavy v 10 sekciách!

Nezmeškajte túto jedinečnú príležitosť na obohatenie svojich vedomostí a podporu našej mladej vedeckej generácie! 🧠

Viac informácií 👇 https://zona.fmph.uniba.sk/studentska-vedecka-konferencia/?fbclid=IwZXh0bgNhZW0CMTAAAR133-5hVnrhWpiCygpC7qaZ8jYbLscoD7DatDQHEq-hGoH_8R3uXVN4xs0_aem_AS3jsQidGoZwV1EE71101SO7pxMd4E0o_1nJ5gQbkaKHdquJkMF9o6Zn09VlpuWobmD3rkF8u60EVOBV5CYOL01N

Študentská vedecká konferencia Študentská vedecká konferencia Študentská vedecká konferencia je každoročnou prehliadkou vedeckých a odborných prác študentov a študentiek bakalárskeho, magisterského aj doktorandského štúdia zo všetkých odborov matematiky, fyziky, informatiky a didaktiky týchto disciplín. V....

✨Another week we are starting with the doctoral colloquium✨

Pavol Kollár with the topic How to count big number of objects exactly

Abstract: Graphs made up of nodes and connections between these nodes are hidden in plain sight everywhere around us. Often times, these graphs look very similar in many distinct places, which one would call a “symmetric” graph. One of the notions of this symmetry is that “every node looks the same”, which is what we call “vertex-transitive graphs”.

A special subclass of these graphs are the “Cayley graphs”, which are graphs that stem from algebraic structures called groups. Ginette Gauyacq in her paper “On quasi-Cayley graphs” introduced a similar but more general structure – the quasi-Cayley graph. Famously, or perhaps infamously, the Petersen graph, which has many interesting properties outside of the topic of our research, is NOT a Cayley graph, but it IS a Quasi-Cayley graph. The Quasi-Cayley graphs can be represented by Latin Squares or, as we call them, regular families of permutations.
Later this structure of Quasi-Cayley graphs and their Latin Square representation was generalised to so-called “r-regular families of permutations” and our research is aimed at generating these families via the use of a computer. However, before enumerating and generating these, we first have to consider HOW MANY we should expect, otherwise we might overflow the memory rather quickly. The topic of the talk is how to use software along with clever mathematical insights to get an upper bound on the counts of these unexplored structures.

More about all colloquia here 👉https://dai.fmph.uniba.sk/w/Doctoral_Colloquia/en

✨Another week we are starting with the doctoral colloquium✨

Marek Šuppa with the topic Multilingual NLP in the Age of LLMs: Are We Done (Yet)?

Abstract: The rise of Large Language Models (LLMs) such as the likes of ChatGPT and GPT-4 took the whole world of computing (not to mention the whole world) by torm. The field of Natural Language Processing (NLP), where many of the ideas crucial for modern development and deployment of LLMs have originated from, was no exception: many tasks considered difficult to solve automatically are now handled by LLMs with relative ease. Despite the successes, there exists a prevailing belief that LLMs' proficiency, particularly in English, is somewhat expected due to their extensive exposure to the English-language internet. This perspective raises questions about the models' performance in multilingual contexts, particularly with languages that have less digital presence.

This presentation will provide an in-depth examination of the current state-of-the-art in LLMs, emphasizing the significance of Slovak, a language with comparatively limited resources, in the current research landscape. We will also present our recent findings, illustrating the role and impact of Slovak in enhancing the understanding and capabilities of LLMs in a multilingual framework. Finally, we will discuss potential future directions in multilingual NLP and/or LLM research, highlighting how insights from languages like Slovak could inform the development of more robust language models.

More about all colloquia here 👇https://dai.fmph.uniba.sk/w/Doctoral_Colloquia/en

✨Another week we are starting with the doctoral colloquium✨

Janka Boborová with the topic Experimental solver employing multiple algorithms to tackle abduction

Abstract: Abduction is one of the inference types that is less explored, therefore, it is interesting to research in the area of ontologies and description logics. The task of abduction is to explain (in the form of facts) an observation (also a fact) using the background knowledge of a problem domain. It has been applied, for example, in medical diagnosis, criminology and model-based diagnosis.

There are few abduction solvers, and even fewer employ more than one abduction algorithm. We have an experimental implementation of an abduction solver, recently dubbed CATS, that included two abduction algorithms: Minimal Hitting Set algorithm (MHS) and MHS-MXP, which is a hybrid combination of MHS and the MergeXplain method (MXP) that is used to speed up the search for explanations. MHS-MXP is a new method that has been developed by our faculty and is still being optimized. On the other hand, the MHS algorithm is well-known but considered outdated. Therefore, we wanted to find newer versions that could be combined with MXP.

Our goal is to expand CATS with more abduction algorithms and their hybrid combination with MXP. Then, propose a proper evaluation and compare them. We also plan to look into optimizing our hybrid approaches.

We researched several algorithms, found newer variants of MHS, and successfully managed to implement one of them (HST) and its hybrid combination (HST-MXP) into our solver. Currently, we are working on optimizing CATS mainly in terms of memory use and major code refactorization. Then, we are ready to implement the second MHS variant called RC-Tree.

More about colloquium here 👇
https://dai.fmph.uniba.sk/w/Doctoral_Colloquia/en

🤖náš kolega Martin Takáč sa minulý týždeň v rámci konferencie ITAPA zúčastnil diskusného panelu AI vo vzdelávaní 👀

Pozrite si záznam tu 👇

AI vo vzdelávaní - Diskusia Umelá inteligencia ako globálny megatrend má multidisciplinárny charakter a výrazne ovplyvní zameranie všetkých študijných odborov. Na túto zmenu sa budú mus...

✨Another week we are starting with the doctoral colloquium✨

Filip Kerák with the topic Modeling nanopore signals

Abstract: While sequencing DNA or RNA with nanopore, the sequencing machine outputs a signal that is later translated to a string over alphabet {A,C,G,T} using machine learning approaches. It has been shown that current approaches to this problem lead to systematic errors in recovered sequences, hindering the downstream analysis. The goal is to develop new methods that can characterize and identify such biases through probabilistic modeling and machine learning.

✨Another week we are starting with the doctoral colloquium✨

Daniel Kyselica with the topic Processing of light curves of satellites and space debris for the purpose of their identification

Abstract: With the increase in space traffic in recent years, precise monitoring of space debris is necessary. Observations in the form of light curves provide us with information about an object’s physical properties including shape, size, surface materials and rotation. Publicly available databases contain a huge amount of gathered light curves that can be used to train machine learning models. Pieces of space debris can fall down to the Earth in a process called reentry, therefore 3D reconstruction of this event can bring more understanding of the physical processes.

For doctoral colloquiums you can also check KAI website:
https://dai.fmph.uniba.sk/w/Doctoral_Colloquia/en

Another week we are starting with the doctoral colloquium:

František Dráček with the topic Anomaly detection from TLE data

Abstract: The burgeoning number of objects in Low Earth Orbit (LEO) poses a critical challenge for satellite operators, demanding robust collision avoidance measures. Although extensive databases track these objects, identifying anomalies within this data is crucial. This research investigates the application of machine learning methods to automatically detect anomalies in satellite data, potentially enhancing space situational awareness and safeguarding future space operations.

This week we have started with doctoral colloquia:

Peter Anthony with the topic Tailoring Logic Explained Network for a Robust Explainable Malware Detection

Abstract:
The field of malware research faces persistent challenges in adopting machine learning solutions due to issues of low generalization and a lack of explainability. While deep learning, particularly artificial neural networks, has shown promise in addressing the generalization problem, their inherent black-box nature poses challenges in providing explicit explanations for predictions. On the other hand, interpretable machine learning models, such as linear regression and decision trees, prioritize transparency but often sacrifice performance. In this work, to address the imperative needs of robustness and explainability in cybersecurity, we propose the application of a recently proposed interpretable-by-design neural network - Logic Explain Network (LEN) to the complex landscape of malware detection. We investigated the effectiveness of LEN in discriminating malware and providing meaningful explanations and evaluate the quality of the explanations over increasing feature size based on fidelity and other standard metrics. Additionally we introduce an improvement on the simplification approach for the global explanation. Our analysis were carried out using static malware features provided by the EMBER dataset. The experimental results shows LEN’s discriminating performance is competitive with Blackbox deep learning models. LEN's Explanations demonstrated high fidelity, indicating genuine reflections of the model's inner workings. However, a notable trade-off between explanation fidelity and compactness is identified.

✨náš kolega Pavel Petrovič sa tento mesiac zúčastnil podujatia Programovanie s LEGOM, ktoré sa sa uskutočnilo na Základnej škole Václava Mitúcha 🏫

Chlapci aj dievčatá naprogramovali prieskumníka, psíka, robota, ktorý sa pohybuje po čiare a pri prekážke zastaví 🤖 Naučili sa veľa nového a užili si veľa zábavy ✨

Viac tu 👉 https://zshsrnie.edupage.org/news/?gtnid=1466 -1466

✨As part of the ongoing TERAIS project, our department has been engaged in multiple research staff exchanges 🤝. Just recently, in November 2023, we hosted researchers from ISTITUTO ITALIANO DI TECNOLOGIA at DAI, and this January, Števo and Iveta, our doctoral candidates, embarked on a three-week journey to the ISTITUTO ITALIANO DI TECNOLOGIA 🌍✈️🤖

Read about exchanges and project TERAIS 👉

News | TERAIS TERAIS (Towards Excellent Robotics and Artificial Intelligence at a Slovak university) is an international project aimed at establishing the Department of Applied Informatics of Comenius University Bratislava, Slovakia as a workplace of international academic excellence. Funded by the Horizon Europe...