Login

1st SMASHING WORKSHOP

7–11 Oct 2024
University of Nova Gorica, Lanthieri mansion, Vipava, Slovenia
Europe/Ljubljana timezone

Contribution List

62 out of 62 displayed
  1. 6. Computational language modelling for cognitive and social science
    Prof. Matthew Purver (Queen Mary Un. of London)
    07/10/2024, 09:00
    Oral presentation
  2. 7. Semi-supervised learning, with applications to biological data analysis
    Prof. Michelangelo Ceci (Department of Computer Science, University of Bari)
    07/10/2024, 09:45
  3. 63. Introdcution
    Gabrijela Zaharijas
    07/10/2024, 11:00
  4. 56. Welcome by the Rector of the UNG
    Prof. Boštjan Golob (UNG)
    07/10/2024, 11:05
  5. 57. A word from the Ministry of Higher Education, Science and Innovation
    Dr Jure Gašparič (MVZI)
    07/10/2024, 11:15
  6. 58. Short presentations from our partners - Jožef Štefan Institute
    Prof. Boštjan Zalar (JSI)
    07/10/2024, 11:30
  7. 59. Short presentations from our partners - University of jubljana FRI
    Prof. Mojca Ciglarič (UL FRI)
    07/10/2024, 11:40
  8. 60. Short presentations from our partners - ARSO
    Prof. Mojca Dolinar (ARSO)
    07/10/2024, 11:50
  9. 61. Concluding remarks by the beneficiary
    Prof. Gabrijela Zaharijas (UNG)
    07/10/2024, 12:00
  10. 62. Q&A with Press
    07/10/2024, 12:05
  11. 44. Social and environmental value assessment of AI/ML technologies (soft-skill lecture)
    Brigita Jurisic (INL, Portugal)
    07/10/2024, 14:00
    Oral presentation
  12. 9. Is computational language modelling linguistics?
    Prof. Tanja Samardžić (Un. of Zurich, Language and Space Lab)
    07/10/2024, 15:00
  13. 41. Is ChatGPT Transforming Academics' Writing Style?
    Mingmeng Geng (SISSA)
    07/10/2024, 16:15
    Contributing talks
    Oral presentation

    Based on one million arXiv papers submitted from May 2018 to January 2024, we assess the textual density of ChatGPT's writing style in their abstracts by means of a statistical analysis of word frequency changes. Our model is calibrated and validated on a mixture of real abstracts and ChatGPT-modified abstracts (simulated data) after a careful noise analysis. We find that ChatGPT is having an...

    Go to contribution page
  14. 34. Upgrading Particulate matter Source apportIonment through Data sciencE
    MARTA VIA GONZALEZ (UNG-CAR)
    07/10/2024, 16:30
    Contributing talks
    Oral presentation

    Particulate Matter (PM) has different severe impacts on human health and climate depending on its size and composition (Yang et al. (2018), Daellenbach et al. (2020)). Source apportionment (SA) is the process of identification of ambient air pollution sources and the quantification of their contribution to pollution levels, and is usually conducted through receptor models (RM). Their usual...

    Go to contribution page
  15. 47. Simulation of particle physics silicon detectors using transformers
    Tadej Novak (Jozef Stefan Institute)
    07/10/2024, 16:45
    Contributing talks
    Oral presentation

    Simulation of physics processes and detector response is a vital part of high energy physics research but also representing a large fraction of computing cost. Generative machine learning is successfully complementing full (standard, Geant4-based) simulation as part of fast simulation setups improving the performance compared to classical approaches.

    A lot of attention has been given to...

    Go to contribution page
  16. 10. Foundation models and scientific discovery in particle physcs
    Prof. Lukas Heinrich (Technical University, Munich)
    07/10/2024, 17:00
  17. 11. Scientific discovery and ML in cosmology
    Prof. Uroš Seljak (UC Berkeley)
    08/10/2024, 09:00
  18. 13. AI for good: Science and Healthcare
    Dr Nenad Tomasev (DeepMind)
    08/10/2024, 09:45
  19. 35. Testing gravity with cosmology
    Emilio Bellini (UNG)
    08/10/2024, 11:00
    Contributing talks
    Oral presentation

    In this talk I will first introduce the main motivations to use cosmological data to test the laws of gravity. I shall focus on the established methods and main results. Finally, I will describe how machine learning can help understanding the fundamental laws of nature.

    Go to contribution page
  20. 1. Characterizing the Fermi-LAT high-latitude sky with simulation-based inference
    Christopher Eckner (Center for Astrophysics and Cosmology, University of Nova Gorica)
    08/10/2024, 11:15
    Contributing talks
    Oral presentation

    The GeV gamma-ray sky, as observed by the Fermi Large Area Telescope (Fermi LAT), harbors a plethora of localized point-like sources. At high latitudes ($|b|>30^{\circ}$), most of these sources are of extragalactic origin. The source-count distribution as a function of their flux, $\mathrm{d}N/\mathrm{d}S$, is a well-established quantity to summarize this population. We employ sequential...

    Go to contribution page
  21. 2. Automatic feature selection and weighting: tree biodiversity estimators explained by other variables
    Romina Wild (Scuola Internazionale Superiore di Studi Avanzati (SISSA) Trieste)
    08/10/2024, 11:30
    Contributing talks
    Oral presentation

    In any large data base, most of the features defining a data point are redundant, irrelevant, or affected by large noise, and have to be discarded. To do this, one needs to answer: What is the best dimensionality of a reduced feature space in order to retain maximum information? How can one correct for different units of measure? What is the optimal scaling of importance between features? We...

    Go to contribution page
  22. 12. Simulation Based Inference applications to astrophysics and cosmology
    Dr Florian List (Un. of Vienna)
    08/10/2024, 11:45
  23. 51. Role of SMEs in SMASH
    Gabrijela Zaharijas
    08/10/2024, 14:15
  24. 52. AI reserach in ARCTUR
    Tomi Iljas
    08/10/2024, 14:30
  25. 53. Cosylab in AI for real time adaptive treatment
    Ado Janse Van Rensburg
    08/10/2024, 14:50
  26. 54. AI reserach in Genialis
    Luka Ausec
    08/10/2024, 15:10

    About Genialis

    Genialis is the RNA biomarker company. They develop and validate clinically actionable biomarkers to help pharmaceutical and diagnostic partners predict patient responses and guide treatment decisions in the field of oncology. Genialis does that by using biology-informed machine learning that models dozens of biological processes from gene expression of cancer patients’...

    Go to contribution page
  27. 26. Data-driven contextual anomaly search: finding infrared-excess in stars
    Gabriella Contardo (SISSA)
    08/10/2024, 15:30
    Contributing talks
    Oral presentation

    "Anomaly detection" covers a broad range of problems and settings. In some instances, it is seen as finding "rare objects", i.e. objects lying in a low-density region of the feature space. However, this task can quickly become difficult, particularly for higher dimensional, noisy or complex (non-rectangular) data where reliable density estimation is non-trivial.
    Additionally, not all...

    Go to contribution page
  28. 30. Modelling the collapse of complex societies
    Sabin Roman (Jožef Stefan Institute)
    08/10/2024, 15:45
    Contributing talks
    Oral presentation

    The talk will cover some key modelling issues that come up when considering the long-term development of societies. Of particular importance is the topic of societal collapse as the archaeological record has numerous instances of the phenomenon. I will discuss some of the general modelling philosophy, relevant literature, my own work on ancient societies (Easter Island, the Maya, Roman Empire...

    Go to contribution page
  29. 48. HF-SCANNER: High frequency sea-level oscillations modeling in the Mediterranean using machine learning
    Iva Međugorac (University of Nova Gorica)
    08/10/2024, 16:00
    Contributing talks
    Oral presentation

    We will present the HF-SCANNER project, detailing the datasets used, the project's goals, and the preliminary results. The HF-SCANNER project aims to develop a fast and accurate forecasting system for high-frequency sea level oscillations (HFOs) and meteotsunamis in the Mediterranean using deep learning and data from both simulations (ECMWF) and observations (sea level and air pressure)....

    Go to contribution page
  30. 45. Meta-learning in evolutionary reinforcement learning: some paths forward
    Bruno Gašperov (University of Ljubljana, Faculty of Computer and Information Science), Bruno Gašperov (University of Ljubljana, Faculty of Computer and Information Science)
    08/10/2024, 16:15
    Contributing talks
    Oral presentation

    Recent years have seen a surge of interest in evolutionary reinforcement learning (evoRL), where evolutionary computation techniques are used to tackle reinforcement learning (RL) tasks. Naturally, many of the existing ideas from meta-RL can also be applied in this context. This is particularly important when handling dynamic (non-stationary) RL environments, where agents need to respond...

    Go to contribution page
  31. 14. Adaptive-Monte Carlo Search and its Application to Science
    Prof. Mark Winands (Maastricht University, Netherlands)
    09/10/2024, 09:00
  32. 15. ML and animal communication
    Prof. Todor Ganchev (Varna Un.)
    09/10/2024, 09:45
  33. 28. HIDRA3: a robust deep-learning model for multi-point ensemble sea level forecasting
    Marko Rus (Slovenian Environment Agency, Office for Meteorology, Hidrology and Oceanography, Ljubljana, Slovenia), Marko Rus
    09/10/2024, 10:30
    Contributing talks
    Oral presentation

    Accurate modeling of sea level and storm surge dynamics with several day-long temporal horizons is essential for effective coastal flood response and the protection of coastal communities and economies. The classical approach to this challenge involves computationally intensive ocean models that typically calculate sea levels relative to the geoid, which must then be correlated with local tide...

    Go to contribution page
  34. 33. Coarse reconstruction with iterative refinement network for sparse spatio-temporal satellite data
    Matjaž Zupančič Muc (Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia)
    09/10/2024, 10:45
    Contributing talks
    Oral presentation

    Sea surface temperature (SST) is critical for weather forecasting and climate modeling, however remotely sensed SST data often suffer from incomplete coverage due to cloud obstruction and limited satellite swath width. While deep learning approaches have shown promise in reconstructing missing data, existing methods struggle to accurately recover fine-grained details, which, however are...

    Go to contribution page
  35. 4. A neural network-based observation operator for weather radar data assimilation
    MARCO STEFANELLI (University of Ljubljana)
    09/10/2024, 11:00
    Contributing talks
    Oral presentation

    One of the most challenging tasks in Numerical Weather Prediction (NWP) is forecasting convective storms. Data Assimilation (DA) methods improve the initial condition and subsequent forecasts by combining observations and previous model forecast (background). Weather radar provides a dense source of observations in storm monitoring. Therefore, assimilating radar data should significantly...

    Go to contribution page
  36. 39. Unlocking European-level HPC-support
    Žiga Zebec (IZUM)
    09/10/2024, 12:00
    Contributing talks
    Oral presentation

    The EPICURE project aims to enhance support for European supercomputer users, particularly within the EuroHPC network. It covers several key areas: code enablement, performance analysis, benchmarking, refactoring and optimization. Each aspect involves porting and refining applications to ensure they scale efficiently across larger node counts in high-performance computing environments. By...

    Go to contribution page
  37. 43. On the representation landscape of large transformer models
    Alberto Cazzaniga (Area Science Park)
    09/10/2024, 12:20
    Contributing talks
    Oral presentation

    Large transformers have been successfully applied to self-supervised data analysis across various data types, including protein sequences, images, and text. However, the understanding of their inner working is still limited. We discuss how, by applying unsupervised learning techniques, we can describe several geometric properties of the representation landscape of these models and how they...

    Go to contribution page
  38. 36. Interpreting Hidden Representations of Transformer Models Through Topological Data Analysis
    Matteo Biagetti (Area Science Park)
    09/10/2024, 12:40
    Contributing talks
    Oral presentation

    This talk addresses the challenge of interpreting the high-dimensional hidden representations in Transformer models, a critical issue given their widespread use in sequential data tasks. We propose using Topological Data Analysis (TDA), a powerful mathematical approach that allows us to understand the shape and structure of complex data. Using TDA, we develop a framework that follows the...

    Go to contribution page
  39. 16. ML in personalized medicine
    Prof. Berend Snijder (ETH Zurich, Institute of Molecular Systems Biology)
    09/10/2024, 13:00
  40. 23. Computational scientific discovery
    Roger Guimera (Universitat Rovira i Virgili, Barcelona)
    10/10/2024, 09:00
  41. 17. ML/AI in particle physics
    Prof. Tilman Plehn (Heidelberg University)
    10/10/2024, 09:45
  42. 46. Using machine learning to search for scalar lepton partners at the LHC
    Patrick Stengel (Jozef Stefan Institute)
    10/10/2024, 11:00
    Contributing talks
    Oral presentation

    We discuss LHC searches for simplified models in which a singlet Majorana dark matter candidate couples to Standard Model leptons through interactions mediated by scalar lepton partners. We summarize the dark matter production mechanisms in these scenarios, highlighting the parameter space which can both satisfy the relic density and account for muon g-2. We focus on the case of intermediate...

    Go to contribution page
  43. 31. Probing the nature of axion-like particles
    Pooja Bhattacharjee (University of Nova Gorica)
    10/10/2024, 11:15
    Contributing talks
    Oral presentation

    Axion-like particles (ALPs) are promising candidates from theories beyond the Standard Model, possibly linked to dark matter. When subjected to external magnetic fields, ALPs can convert to photons and vice versa, rendering them observable. The ALP-photon mixing distorts the gamma-ray blazar spectra with measurable effects, albeit tiny. The description of blazar jets varies per target and...

    Go to contribution page
  44. 5. Leveraging Machine Learning to Detect Dark Matter Subhalos in the Milky Way
    María Benito (Tartu observatory, University of Tartu)
    10/10/2024, 11:30
    Contributing talks
    Oral presentation

    Dark matter remains a crucial missing piece in our understanding of the Universe. Since the late 1970s, the astrophysics community has widely accepted that visible galaxies lie at the centre of large dark matter halos. Significant progress has been made in understanding the halo that hosts our own Milky Way galaxy, including its overall mass and density distribution. However, the halos...

    Go to contribution page
  45. 20. ML in biomedical research
    Lucia Sacchi (Un. of Pavia)
    10/10/2024, 11:45
  46. 21. How to write grant applications (soft skill lecture)
    Paul McGuiness
    10/10/2024, 14:00
  47. 42. Machine Learning-Guided Nanobody Discovery for Enhanced Biomarker Research
    Klara Kropivsek (Laboratory for Environmental and Life Sciences, University of Nova Gorica)
    10/10/2024, 15:00
    Contributing talks
    Oral presentation

    The integration of machine learning (ML) with advanced biomarker discovery techniques offers new opportunities for pathology, particularly in personalized medicine. This research will focus on using nanobodies—small, stable, and highly specific single-domain antibodies derived from camelids—as versatile tools for advancing biomarker research. We plan to utilize ML to explore a diverse, naïve...

    Go to contribution page
  48. 3. Normalizing flows for evidence estimation
    Rahul Srinivasan (SISSA, Italy)
    10/10/2024, 15:15
    Contributing talks
    Oral presentation

    I introduce floZ, an improved method based on normalizing flows, for estimating the Bayesian evidence (and its numerical uncertainty) from samples drawn from the unnormalized posterior distribution. I validate it on distributions whose evidence is known analytically, up to 15 parameter-space dimensions and I demonstrate its accuracy for up to 200 dimensions with $10^5$ posterior samples. I...

    Go to contribution page
  49. 32. Detecting faint VHE gamma-ray sources using Deep Neural Networks
    Judit Pérez Romero (CAC/UNG)
    10/10/2024, 15:30
    Contributing talks
    Oral presentation

    The detection of faint γ-ray sources is an historical challenging task for the very-high energy astrophysics community. The standard approaches to identify sources rely on likelihood analyses. However, our lack of knowledge of background uncertainties can introduce strong biases in the results and hinder a detection. The field of machine learning (ML) has advanced dramatically over the past...

    Go to contribution page
  50. 27. Looking for anomalous variability: wandering unsupervised
    Oleksandra Razim (Ruder Boscovic Institute)
    10/10/2024, 15:45
    Contributing talks
    Oral presentation

    Astronomical datasets include millions, sometimes billions of records, and in order to handle such volumes of data in the last 20 years astronomers actively use ML methods for various classification and characterization tasks. However, most of those applications utilize supervised ML, which requires large pre-existing training samples. Obtaining those training samples is a complicated task,...

    Go to contribution page
  51. 22. ML and survey science in astro
    Mario Jurić (Un. of Washington)
    10/10/2024, 16:30
  52. 49. From Blurry to Brilliant: How Generative AI is Transforming the Way We See Images
    Nikki Martinel (Un. of Udine)
    11/10/2024, 09:00
  53. 37. PCA analysis for absorption measurements correction schemes– A test study
    JESUS YUS DIEZ (Univerza v Novi Gorici)
    11/10/2024, 09:45
    Contributing talks
    Oral presentation

    Light absorbing carbonaceous aerosols (LAC) contribute positive forcing to the Earth radiative budget, which results in atmospheric warming. To determine the actual contribution of LAC aerosols, measurements from across the globe are incorporated into climate models. The most used approach for this measurement is by using filter-photometers (FP), which measure the attenuation of light through...

    Go to contribution page
  54. 40. Towards an Automatic Source Detection Pipeline in the Galactic Plane Survey by CTA using Deep Learning
    Zoja Rokavec
    11/10/2024, 10:00
    Contributing talks
    Oral presentation

    The Galactic Plane Survey (GPS) as proposed by CTAO is one of the key science projects that will cover an energy range from ~30 GeV to ~100 TeV with unprecedented sensitivity leading to an increase in the known gamma-ray source population by a factor of five.
    Here we tested our deep-learning-based automatic source detection techniques and compared them with traditional likelihood detection...

    Go to contribution page
  55. 29. Multi-Messenger and Multi-Wavelength emission from Galaxy Clusters hosting AGNs using Machine Learning Techniques
    Saqib Hussain (University of Nova Gorica)
    11/10/2024, 10:15
    Contributing talks
    Oral presentation

    This work is dedicated to develop the most detailed comprehensive numerical framework to date, combining magnetohydrodynamics (MHD) and Monte-Carlo simulations to derive the multi-wavelength (MWL) and multi-messenger spectra from the magnetized environment of galaxy clusters. Special attention will be given to Perseus-like clusters hosting active galactic nuclei (AGNs). We will study...

    Go to contribution page
  56. 55. Inverse systems approach to design Secure Random Communications Systems
    Dr Areeb Ahmed (University of Ljubljana)
    11/10/2024, 10:30
    Oral presentation

    This contribution presents an enhanced approach to secure communications using multiple inverse systems to design alpha-stable noise based Random communication systems (RCSs). This method incorporates multiple inverse systems to transform the encoded alpha stable noise signals on the transmitter side with corresponding inverse systems on the receiver side to decode the retrieved signals...

    Go to contribution page
  57. 24. Social media for scientists (soft-skill lecture)
    Laura Busato (SISSA Medialab)
    11/10/2024, 11:15
  58. 50. Q&A with the SMASH PI for the Fellows
    11/10/2024, 12:45
  59. 8. A word about SMASH from our partner and funding institutons (including Q&A from the press)
    Prof. Boštjan Golob (University of Nova Gorica)
    Oral presentation
  60. 18. Computer vision and science applications
  61. 19. Multi-layer perceptron in atmospheric physics
    Baseerat Romshoo (Leibniz Institute for Tropospheric Research, TROPOS)
  62. 25. Workshop summary