BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:EuroCC Tutorial on Using Large Language Models (LLM) for Private D
 ata - part 1
DTSTART;VALUE=DATE-TIME:20240607T113000Z
DTEND;VALUE=DATE-TIME:20240607T131500Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1544@events.ncbj.gov.pl
DESCRIPTION:Speakers: Krzysztof Nawrocki (National Centre for Nuclear Rese
 arch)\nThe tutorial will explore the possibilities of utilizing LLMs for i
 nteracting with private data. We will introduce tools that enable harnessi
 ng the power of generative AI in scenarios where no data can leave your ex
 ecution environment at any point. We explore the architecture and data req
 uirements for creating your private ChatGPT\, leveraging semantic understa
 nding while maintaining control over your data.\n\n**Hands-on requirements
 **: laptop with working Wi-Fi\, up-to-date web browser\, SSH client.\n\n\n
 \nhttps://events.ncbj.gov.pl/event/314/contributions/1544/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1544/
END:VEVENT
BEGIN:VEVENT
SUMMARY:AI meets physics - an overview of AI applications in the context o
 f Monte Carlo particle transport simulations
DTSTART;VALUE=DATE-TIME:20240605T070000Z
DTEND;VALUE=DATE-TIME:20240605T074000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1569@events.ncbj.gov.pl
DESCRIPTION:Speakers: Nils Krah (INSA Lyon)\nhttps://events.ncbj.gov.pl/ev
 ent/314/contributions/1569/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1569/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Towards total-body J-PET: overview of data correction techniques f
 or image reconstruction
DTSTART;VALUE=DATE-TIME:20240605T134000Z
DTEND;VALUE=DATE-TIME:20240605T140500Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1568@events.ncbj.gov.pl
DESCRIPTION:Speakers: Aurélien Coussat ()\nPositron Emission Tomography (
 PET) is a widely employed medical imaging technique that uses radiotracers
  to visualise various metabolic processes. PET functions by detecting gamm
 a rays resulting from the decay of the radiotracer in the patient body. Th
 e acquired data are then utilised to reconstruct an image representing the
  initial radiotracer distribution. However\, numerous effects\, including 
 accidental coincidences\, photon scattering or positron range\, affect the
  data in ways that cause artefacts in the reconstructed image. A number of
  data correction techniques exist to compensate for these undesired effect
 s and produce images of satisfactory quality. This talk will review existi
 ng techniques\, with a focus on the total-body Jagiellonian PET\, a protot
 ype of a long-AFOV PET system that uses plastic scintillators currently un
 der development at the Jagiellonian University in Poland.\n\nhttps://event
 s.ncbj.gov.pl/event/314/contributions/1568/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1568/
END:VEVENT
BEGIN:VEVENT
SUMMARY:From Signal Acquisition to Image Reconstruction: Potential Applica
 tions of Machine Learning in Positron Emission Tomography
DTSTART;VALUE=DATE-TIME:20240606T070000Z
DTEND;VALUE=DATE-TIME:20240606T074000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1567@events.ncbj.gov.pl
DESCRIPTION:Speakers: Georg Schramm ()\nPositron Emission Tomography (PET)
  is a functional medical imaging technique that allows for the visualizati
 on and measurement of metabolic processes in the body by detecting pairs o
 f 511-keV gamma rays originating from a tracer molecule\nlabeled with a po
 sitron emitter.\n\nDespite its advanced capabilities\, PET imaging faces s
 ignificant challenges\, including high noise levels and limited spatial re
 solution of the acquired data\, which severely hampers the diagnostic qual
 ity of the reconstructed images.\n\nIn addition to classical algorithms tr
 aditionally used for signal processing\, image reconstruction\, and image 
 post-processing\, machine learning (ML) based algorithms are now being exp
 lored to enhance the quality of PET raw data and the quality of reconstruc
 ted PET images.\n\nThis talk provides an overview of the current applicati
 ons of ML in PET imaging\,\nencompassing various stages from signal acquis
 ition to image reconstruction and post-processing.\n\nAdditionally\, the p
 resentation addresses the current challenges in the field and explores fut
 ure needs and directions for a sustainable and successful integration of M
 L in PET imaging.\n\nhttps://events.ncbj.gov.pl/event/314/contributions/15
 67/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1567/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Generic ML for fast simulations
DTSTART;VALUE=DATE-TIME:20240604T144000Z
DTEND;VALUE=DATE-TIME:20240604T151000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1558@events.ncbj.gov.pl
DESCRIPTION:Speakers: Michał Mazurek (National Centre for Nuclear Researc
 h)\nIn the field of high energy physics\, Monte Carlo simulations play a k
 ey role in interpreting physics results\, as well as the design of new det
 ectors. Leveraging machine learning for fast simulation is essential for g
 enerating the required amount of simulated samples. Nevertheless\, transit
 ioning from initial models to full-scale productions is usually a very cha
 llenging task.\n\nIn this talk\, we will show how to use Gaussino\, an exp
 eriment-agnostic core simulation framework\, to streamline the incorporati
 on of machine learning models for fast simulations: starting from an early
 \, generic prototype to a fully deployed model used in production at scale
 . We will also present one of the first implementations of ML-based fast s
 imulation models based on the CaloChallenge initiative\, trained and valid
 ated on the LHCb electromagnetic calorimeter\, and finally integrated with
 in the LHCb simulation framework.\n\nhttps://events.ncbj.gov.pl/event/314/
 contributions/1558/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1558/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Astrophysics of the nearest future: big data and machine learning 
 challenges
DTSTART;VALUE=DATE-TIME:20240607T083500Z
DTEND;VALUE=DATE-TIME:20240607T091500Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1565@events.ncbj.gov.pl
DESCRIPTION:Speakers: Agnieszka Pollo (National Centre for Nuclear Researc
 h AND Jagiellonian University)\nIt is often said that we are now living in
  an era of astronomical "big data"\, with the amount of observational data
  increasing by orders of magnitudes during the last decades\, ane expected
  to increase even much faster in the coming years\, with the advent of hug
 e wide field observatories\, like  Vera Rubin Observatory or The Square Ki
 lometre Array Observatory. With hundreds of petabytes of new data appearin
 g every year\, machine learning becomes a necessity. At the same time\, th
 e application of machine learning methods to astrophysical problems yields
  many specific challenges: small and not fully representative training sam
 ples\, physical interpretability\, or effective search for anomalies. I wi
 ll discuss the aims\, difficulties\, and approaches that are being develop
 ed\, making use\, among other things\, of examples from the research made 
 in our extragalactic astrophysics group in NCBJ and UJ.\n\nhttps://events.
 ncbj.gov.pl/event/314/contributions/1565/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1565/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Quantum computing of gauge fields
DTSTART;VALUE=DATE-TIME:20240606T090000Z
DTEND;VALUE=DATE-TIME:20240606T094000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1564@events.ncbj.gov.pl
DESCRIPTION:Speakers: Jakub Mielczarek (Jagiellonian University)\nThis tal
 k aims to explore the relation between gauge fields\, which are at the bas
 is of our understanding of fundamental interactions (including gravity) an
 d quantum information. Our primary focus is on SU(2) gauge fields\, where 
 a spin network representation of gauge-invariant states is possible. The s
 pin network framework offers a unique perspective on the entanglement stru
 cture inherent in gauge theories. Additionally\, representing these states
  through quantum circuits paves the way for simulating non-abelian field t
 heories using quantum computers. We will present the results from quantum 
 simulations of simple SU(2) gauge field configurations on IBM's 5-qubit (Y
 orktown) and 15-qubit (Melbourne) superconducting quantum computers.\n\nht
 tps://events.ncbj.gov.pl/event/314/contributions/1564/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1564/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Polish National Competence Centre in HPC: Enabling AI in EuroHPC
DTSTART;VALUE=DATE-TIME:20240605T100500Z
DTEND;VALUE=DATE-TIME:20240605T103500Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1566@events.ncbj.gov.pl
DESCRIPTION:Speakers: Marek Magrys (Cyfronet)\nThis presentation delves in
 to the importance of the EuroHPC Joint Undertaking and the supercomputing 
 resources it provides for European users from industry\, science and publi
 c administration. In particular\, it highlights the LUMI supercomputer\, r
 anked 5th on the recent Top500 list of the fastest supercomputers\, making
  it the fastest supercomputer in Europe. The EuroCC2 project is also intro
 duced as a critical initiative in fostering HPC competencies in Europe\, w
 ith the Polish National Competence Centre activities in Poland described i
 n more detail. A focal point of the presentation is the SpeakLeash project
 \, a compelling example of AI utilization facilitated by NCC Poland\, demo
 nstrating how cutting-edge HPC resources can be harnessed to drive innovat
 ive AI solutions.\n\nhttps://events.ncbj.gov.pl/event/314/contributions/15
 66/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1566/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Working with large language models using Megatron-DeepSpeed on LUM
 I
DTSTART;VALUE=DATE-TIME:20240603T120000Z
DTEND;VALUE=DATE-TIME:20240603T140000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1563@events.ncbj.gov.pl
DESCRIPTION:Speakers: Maciej Szpindler (ACK Cyfronet)\nThis builds up on d
 etails from the first part to setup specific environment for LLM processin
 g. It uses Megatron-DeepSpeed framework to experiment with pretrained data
  for prompt engineering tasks.\n\nhttps://events.plgrid.pl/event/55/\n\nht
 tps://events.ncbj.gov.pl/event/314/contributions/1563/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1563/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Using machine learning frameworks on LUMI
DTSTART;VALUE=DATE-TIME:20240603T080000Z
DTEND;VALUE=DATE-TIME:20240603T110000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1562@events.ncbj.gov.pl
DESCRIPTION:Speakers: Maciej Szpindler (ACK Cyfronet)\nLUMI is one of the 
 largest European supercomputers and flagship EuroHPC systems. It is unifie
 d\, heterogeneous computing infrastructure aiming at large\, accelerated w
 orkflows. One of the key elements of its computing architecture is acceler
 ator type and its programming environment. This half-day workshop is prese
 nting typical transition steps from common clusters and cloud resources to
 gether with use cases with both traditional HPC workloads and fundamental 
 elements for running large models with machine learning frameworks.\n\nThi
 s part shows how to setup environment for AI workflows on a real supercomp
 uting system. It combines common HPC tools with popular machine learning f
 rameworks relying on GPU offloading and multiprocessing across multiple co
 mputing nodes.\n\nhttps://events.plgrid.pl/event/55/\n\nhttps://events.ncb
 j.gov.pl/event/314/contributions/1562/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1562/
END:VEVENT
BEGIN:VEVENT
SUMMARY:LUMI: Europe's most powerful supercomputer
DTSTART;VALUE=DATE-TIME:20240605T090000Z
DTEND;VALUE=DATE-TIME:20240605T094000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1560@events.ncbj.gov.pl
DESCRIPTION:Speakers: Tomasz Malkiewicz (CSC / NeIC)\nThe EuroHPC Joint Un
 dertaking has installed three leadership-class supercomputers. We will dis
 cuss one of these systems\, LUMI\, located in Kajaani\, Finland. LUMI is c
 urrently the fastest supercomputer in Europe and in general one of the mos
 t powerful and advanced computing systems in the world. In this talk\, I w
 ill present the technical architecture of the LUMI infrastructure and its 
 status\, together with plans and ambitions for the near future. Then\, an 
 overview of the scientific showcases and achievements from the first month
 s of LUMI will be presented. These include\, for example\, contributions t
 o the Destination Earth initiative\, work on large language models and bre
 akthroughs from extreme-scale computing capabilities in many fields of com
 putational science.\n\nhttps://events.ncbj.gov.pl/event/314/contributions/
 1560/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1560/
END:VEVENT
BEGIN:VEVENT
SUMMARY:FPGAs in HPC - applications and methods
DTSTART;VALUE=DATE-TIME:20240605T113000Z
DTEND;VALUE=DATE-TIME:20240605T115500Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1557@events.ncbj.gov.pl
DESCRIPTION:Speakers: Grzegorz Korcyl (Jagiellonian University)\nIn recent
  years\, Field Programmable Gate Array technology has gained momentum in t
 he HPC sector as the abundance of configurable resources and high-level de
 velopment tools allow to implement complex algorithmics. Unique features o
 f this technology such as adaptable computing\, pipelined processing and i
 ntegrated high-speed transceivers provide means to compete with classic CP
 Us or GPUs in certain applications. In this talk\, I will present the tech
 nology fundamentals\, development methodologies and overview the computing
  areas that can benefit from employing FPGAs.\n\nhttps://events.ncbj.gov.p
 l/event/314/contributions/1557/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1557/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Improvement of time-of-flight resolution of PET scanner using addi
 tional prompt photon
DTSTART;VALUE=DATE-TIME:20240605T131500Z
DTEND;VALUE=DATE-TIME:20240605T134000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1554@events.ncbj.gov.pl
DESCRIPTION:Speakers: Lech Raczyński (National Centre for Nuclear Researc
 h)\nPositronium Imaging (PI) has become one of the most prospective branch
  of Positron Emission Tomography. During the PI measurement two classes of
  events are required: double-coincidence events originated from pair of ba
 ck-to-back annihilation photons and triple-coincidence events comprised wi
 th three photons\, i.e\, two annihilation photons and one additional promp
 t photon. The standard reconstruction of the emission position along the l
 ine-of-response of triple-coincidence event is the same as in the case of 
 double-coincidence event and is based on times and positions of two annihi
 lation photons only\; an information introduced by the additional prompt p
 hoton is ignored. In this presentation\, we propose to extend the reconstr
 uction of position of triple-coincidence event by taking into account the 
 time and position of prompt photon. Moreover\, we incorporate the knowledg
 e about the positronium lifetime distribution and derive the algorithm for
  the position reconstruction. We discuss the limitations of the method bas
 ed on the simulation data.\n\nhttps://events.ncbj.gov.pl/event/314/contrib
 utions/1554/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1554/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Entanglement classification via Neuronal Networks
DTSTART;VALUE=DATE-TIME:20240606T115500Z
DTEND;VALUE=DATE-TIME:20240606T122000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1532@events.ncbj.gov.pl
DESCRIPTION:Speakers: Christopher Popp (University Vienna)\nIn this talk\,
  we investigate the application of machine learning to\nan NP-hard problem
  in quantum information theory\, the separability\nproblem of classifying 
 a quantum state as entangled or\nseparable. This problem arises for entang
 led\nquantum systems of dimension three or higher\, where no exact solutio
 n\nis currently known. We demonstrate that neural networks can accurately 
 classify mixtures\nof Bell states. This classification can be achieved by 
 \nconsidering the properties of the mixtures themselves and\nby entropy-re
 lated quantities.We further highlight convolutional neural networks in thi
 s\nprocess. Our findings indicate that these networks can reflect\nentangl
 ement structures crucial for accurate \nclassification. The study undersco
 res the synergistic potential of machine learning\nand quantum information
  science. It suggests a promising direction for\ntheir combined applicatio
 n in solving complex quantum problems.\n\nhttps://events.ncbj.gov.pl/event
 /314/contributions/1532/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1532/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Quantum Computing Hardware with QGates
DTSTART;VALUE=DATE-TIME:20240606T125000Z
DTEND;VALUE=DATE-TIME:20240606T145000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1546@events.ncbj.gov.pl
DESCRIPTION:Speakers: Beatrix Hiesmayr (University of Vienna)\nIn this wor
 kshop\, a modular hardware will be presented that enables an introduction 
 to the basic algorithms of quantum computing such as the Shor algorithm (f
 actorization of 15 and 21)\, the Grover algorithm\, the quantum K-means al
 gorithm\, etc. The low-cost hardware is based on microcontrollers and enab
 les exact quantum simulations of quantum circuits with up to 8 qubits with
  so-called "QGates". The modular design consisting of several identical bo
 ards enables the complexity to be cascaded and thus a didactic introductio
 n to the complexity and challenges of the upcoming quantum computers.\n\nh
 ttps://events.ncbj.gov.pl/event/314/contributions/1546/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1546/
END:VEVENT
BEGIN:VEVENT
SUMMARY:EuroCC Tutorial on Using Large Language Models (LLM) for Private D
 ata - part 2
DTSTART;VALUE=DATE-TIME:20240607T134500Z
DTEND;VALUE=DATE-TIME:20240607T153000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1545@events.ncbj.gov.pl
DESCRIPTION:Speakers: Krzysztof Nawrocki (National Centre for Nuclear Rese
 arch)\nThe tutorial will explore the possibilities of utilizing LLMs for i
 nteracting with private data. We will introduce tools that enable harnessi
 ng the power of generative AI in scenarios where no data can leave your ex
 ecution environment at any point. We explore the architecture and data req
 uirements for creating your private ChatGPT\, leveraging semantic understa
 nding while maintaining control over your data.\n\n**Hands-on requirements
 **: laptop with working Wi-Fi\, up-to-date web browser\, SSH client.\n\nht
 tps://events.ncbj.gov.pl/event/314/contributions/1545/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1545/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Reconstruction of muon bundles in KM3NeT detectors using machine l
 earning methods
DTSTART;VALUE=DATE-TIME:20240607T100500Z
DTEND;VALUE=DATE-TIME:20240607T103000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1530@events.ncbj.gov.pl
DESCRIPTION:Speakers: Piotr Kalaczyński (CAMK PAN)\nThe network of two ne
 xt-generation underwater Cherenkov neutrino telescopes: ARCA and ORCA is b
 eing successively deployed in the Mediterranean Sea by the KM3NeT Collabor
 ation. The focus of ARCA is neutrino astronomy\, while ORCA is mainly dedi
 cated to neutrino oscillation studies. Both detectors are already operatio
 nal in their intermediate states and collect valuable results\, including 
 the measurements of the atmospheric muons produced by cosmic ray interacti
 ons. This work explores the potential of intermediate as well as complete 
 detector configurations of ARCA and ORCA to observe events composed of mul
 tiple muons\, originating from a common primary cosmic ray\, called muon b
 undles. An approach to infer the total number of observed muons in a bundl
 e as well as their total energy and even the energy of the primary will be
  presented.\n\nhttps://events.ncbj.gov.pl/event/314/contributions/1530/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1530/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Using Machine Learning to Identify outliers in the Fundamental Met
 allicity Relation.
DTSTART;VALUE=DATE-TIME:20240607T094000Z
DTEND;VALUE=DATE-TIME:20240607T100500Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1495@events.ncbj.gov.pl
DESCRIPTION:Speakers: Francesco Pistis (National Centre for Nuclear Resear
 ch)\nThe chemical evolution of galaxies is intricately linked to the inter
 play between Active Galaxy Nuclei (AGNs) and galactic interactions. This i
 s exemplified in the fundamental metallicity relation (FMR) which characte
 rizes the chemical evolution of galaxies where stars are formed. Although 
 AGN feedback is reflected in the FMR\, galaxies that host AGNs follow the 
 same relation as those that are star-forming. However\, interacting galaxi
 es\, such as pairs or mergers\, seem to constitute a distinctive populatio
 n that deviates from the FMR. Our objective is to identify outliers throug
 h machine-learning algorithms that scour for correlations with incorrectly
  classified galaxy types or interaction statuses.\n\nhttps://events.ncbj.g
 ov.pl/event/314/contributions/1495/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1495/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Characteristic sky background features around galaxy mergers
DTSTART;VALUE=DATE-TIME:20240607T091500Z
DTEND;VALUE=DATE-TIME:20240607T094000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1498@events.ncbj.gov.pl
DESCRIPTION:Speakers: Luis Eduardo Suelves (National Centre for Nuclear Re
 search)\nGalaxy merger identification in large-scale surveys is one of the
  main areas of Astronomy that are benefitting from the development of Mach
 ine Learning (ML)\, especially for galaxy classification. In this talk\, I
  will focus on the combination of ML\, clustering\, and dimensionality red
 uction techniques\, with astronomical images and measurements. The goal of
  this methodology is to discern galaxy mergers from the rest of galaxies i
 n the sky. An initial Neural Network was applied to the flux measurements 
 from the images\, and the iteration on multiple combinations of these para
 meters led us to find how one parameter traced galaxy mergers with a test-
 set accuracy of up to 91 %. This parameter is the error in the sky backgro
 und measurement\, which we interpret to trace low signal-to-noise features
  around observed galaxies. With this work\, I want to stress the benefits 
 of interpreting the results of ML models and how it led us to unveil a com
 pletely new path for galaxy morphology classification.\n\nhttps://events.n
 cbj.gov.pl/event/314/contributions/1498/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1498/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Auto Quantum Machine Learning with AQMLator
DTSTART;VALUE=DATE-TIME:20240607T074000Z
DTEND;VALUE=DATE-TIME:20240607T080500Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1506@events.ncbj.gov.pl
DESCRIPTION:Speakers: Tomasz Rybotycki (SRI PAS\, NCAC PAS\, CEAI AGH)\nSi
 nce the 2010s\, when deep learning became feasible\, machine learning (ML)
  has been experiencing ever-growing attention. The ability to teach large 
 ML models gave rise to various neural network architectures\, such as conv
 olutional neural networks or generative adversarial networks. Around the s
 ame time\, technological advancements allowed us to also direct our attent
 ion to quantum computing (QC)\, a computation paradigm that uses quantum m
 echanical phenomena. Naturally\, quantum and hybrid ML models began to app
 ear\, and with them\, a daunting task -- how to design the architecture fo
 r such models?\n\nWe present AQMLator\, an Auto Quantum Machine Learning p
 latform. It aims to automatically propose and train the quantum layers of 
 an ML model with minimal input from the user. This way\, AI scientists can
  overcome the entry barrier for QC and use quantum machine learning (QML) 
 or hybrid models. AQMLator uses standard ML Python libraries\, making it e
 asy to introduce into existing ML pipelines.\n\nhttps://events.ncbj.gov.pl
 /event/314/contributions/1506/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1506/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Machine Learning based on quantum or classical systems: a comparis
 on
DTSTART;VALUE=DATE-TIME:20240607T070000Z
DTEND;VALUE=DATE-TIME:20240607T074000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1531@events.ncbj.gov.pl
DESCRIPTION:Speakers: Beatrix Hiesmayr (University of Vienna)\nIt is well 
 known that quantum laws are fundamentally different and are currently bein
 g used to boost the performance of computers\, including machine learning 
 algorithms. We elaborate on the differences and challenges from different 
 perspectives. Furthermore\, we point out that with the recent trend in res
 earch to publish the computer code along with the research results\, a cau
 sal link between the (formal) mathematical model and the set of results ca
 n no longer be certain. This is especially true for the recent advances in
  AI-driven applications.\n\nhttps://events.ncbj.gov.pl/event/314/contribut
 ions/1531/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1531/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Quantum Neural Networks: current status and next steps
DTSTART;VALUE=DATE-TIME:20240606T113000Z
DTEND;VALUE=DATE-TIME:20240606T115500Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1528@events.ncbj.gov.pl
DESCRIPTION:Speakers: Tobias Christoph Sutter (University of Vienna)\nClas
 sical machine learning has proven valuable since its implementation on cla
 ssical computers became feasible. On the other hand\, quantum computation 
 claims to present an exponential advantage over any classical algorithm fo
 r specialized tasks. Thus\, adapting the machine learning paradigm to the 
 quantum realm is a promising way forward.\nWe start the talk with a genera
 l introduction to the mathematical framework required for this adaptation.
  These basic notions are crucial to understanding how we can manipulate qu
 antum systems and what the limitations are. Afterward\, we discuss differe
 nt approaches to "quantizing" the neural network architecture\, i.e.\, ada
 pting classical neural networks to quantum systems\, before focusing on Di
 ssipative Quantum Neural Networks. We show that this ansatz has the potent
 ial to be a "quantum universal approximator" as it can be used to learn an
 y quantum operation. Lastly\, preliminary numerical results and possible n
 ext steps are discussed.\n\nhttps://events.ncbj.gov.pl/event/314/contribut
 ions/1528/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1528/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Parallel Two-Qubit Gates on IQM Resonance: Garnet 20-Qubit Quantum
  Computer
DTSTART;VALUE=DATE-TIME:20240606T100500Z
DTEND;VALUE=DATE-TIME:20240606T103000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1503@events.ncbj.gov.pl
DESCRIPTION:Speakers: Jakub Mrożek (IQM Quantum Computers)\nThe promise o
 f quantum computing speeding up the execution of certain computational tas
 ks cannot be achieved without quality hardware. Superconducting qubits are
  one of the most mature technologies for an implementation of a quantum pr
 ocessing unit (QPU)\, and such devices are already available to be used by
  researchers in cloud. Among them is IQM's Garnet QPU available on Resonan
 ce platform. This 20-qubit quantum computer represents IQM's core technolo
 gy choices\, such as a floating tunable transmon coupler [1]\, allowing QP
 U median CZ gate fidelity of 99.5% and entangling all the qubits on the ch
 ip by preparing a GHZ state with 62% fidelity. I will present benchmarking
  results ranging from fidelities to application benchmarks quantifying per
 formance in certain tasks. Subsequently\, I will describe the tunable coup
 ler architecture\, and the methods for fast\, reliable and automatic calib
 ration of high-fidelity parallel two-qubit gates.\n[1] Fabian Marxer et al
 . PRX Quantum 4 010314 (2023)\n\nhttps://events.ncbj.gov.pl/event/314/cont
 ributions/1503/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1503/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Utilizing Superconducting Quantum Computer for Education and Resea
 rch
DTSTART;VALUE=DATE-TIME:20240606T094000Z
DTEND;VALUE=DATE-TIME:20240606T100500Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1499@events.ncbj.gov.pl
DESCRIPTION:Speakers: Jami Rönkkö (IQM Quantum Computers)\nWith a growin
 g interest in quantum technology globally\, there is an increasing\nneed f
 or accessing relevant physical systems for education and research. This ta
 lk introduces a commercially available on-site quantum computer utilizing 
 superconducting technology. We show how this system can be used in educati
 on to\nteach quantum concepts and deepen understanding of quantum theory a
 nd quantum computing. It offers learning opportunities for future talent a
 nd contributes\nto fundamental research and technological progress. We hig
 hlight the advantages of having complete hands-on access to the hardware. 
 As educational and research use cases we demonstrate the violation of CHSH
  inequality\, a GHZ state experiment offering intuitive account for decohe
 rence and simulation of neutrino flavor oscillations.\n\nhttps://events.nc
 bj.gov.pl/event/314/contributions/1499/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1499/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Machine Learning-based Scatter Correction for a Dual-Panel Positro
 n Emission Mammography Scanner
DTSTART;VALUE=DATE-TIME:20240606T080500Z
DTEND;VALUE=DATE-TIME:20240606T083000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1496@events.ncbj.gov.pl
DESCRIPTION:Speakers: Fernando Moncada-Gutiérrez (Instituto de Física\, 
 UNAM)\nPositron Emission Mammography (PEM) is a Nuclear Medicine technique
  for breast imaging based on a dedicated scanner assembled with parallel d
 ual-panel detector arrays. Patient positioning in close contact with the s
 canner enhances spatial resolution and sensitivity in comparison with ring
 -based scanners\, but this geometry hinders the adaptation of conventional
  attenuation and scatter correction methods\, which affects the quantitati
 ve assessment of studies. In this work we trained several machine learning
  algorithms for scatter correction with list-mode data from a Monte Carlo 
 simulation of a PEM prototype being built in our lab. The features for thi
 s binary classification problem were energy and position of detection\, wh
 ere energy had the higher feature importance in agreement with traditional
  methods. The best results were found with a Random Forest of 38 estimator
 s and a maximum depth of 7\, which reduced the scatter fraction of a study
  of 1 million events from 11% to 4% in 2 seconds.\n\nhttps://events.ncbj.g
 ov.pl/event/314/contributions/1496/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1496/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Using 3D CNNs for distortion corrections in PET imaging
DTSTART;VALUE=DATE-TIME:20240606T074000Z
DTEND;VALUE=DATE-TIME:20240606T080500Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1494@events.ncbj.gov.pl
DESCRIPTION:Speakers: Konrad Klimaszewski (National Centre for Nuclear Res
 earch)\nIn Positron Emission Tomography the problem of image distortion du
 e to scattered photons or accidental coincidences becomes more pronounced 
 for large field-of-view scanners capable of measuring the whole patient in
  one scan. We propose a novel method of encoding coincidence event informa
 tion to enhance the efficiency of noise filtration classification. The pro
 posed encoding enables the usage of Convolutional Neural Networks as featu
 re extractors in the classification task. We take advantage of the voxel n
 ature of underlying data and evaluate the performance of the 3-D CNN netwo
 rk to classify true\, scattered and accidental coincidences for imaging qu
 ality improvement with large field-of-view PET scanners.\n\nhttps://events
 .ncbj.gov.pl/event/314/contributions/1494/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1494/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Assessment of Internal Radiation Dose: Understanding the Influence
  of Respiratory Motion
DTSTART;VALUE=DATE-TIME:20240605T140500Z
DTEND;VALUE=DATE-TIME:20240605T143000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1501@events.ncbj.gov.pl
DESCRIPTION:Speakers: Moncef ATI (University Of Oran1)\nAssessing radiatio
 n doses to internal organs is crucial in evaluating the risks and benefits
  of diagnostic and therapeutic nuclear medicine procedures\, such as PET\,
  for patients. Respiratory motion causes significant displacement of inter
 nal organs\, affecting the absorbed dose in cases of external r adiation e
 xposure. In this study\, our focus was on determining the role of respirat
 ory motion in assessing the absorbed dose of S values for Lu177\, Dy 165\,
  I 131\, and Tc99m. Despite this\, there has been no previous report on th
 e impact of respiratory motion on internal radiation dosimetry\n\nhttps://
 events.ncbj.gov.pl/event/314/contributions/1501/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1501/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Advanced TOF MLEM reconstruction of a human patient scanned by the
  modular J-PET
DTSTART;VALUE=DATE-TIME:20240605T125000Z
DTEND;VALUE=DATE-TIME:20240605T131500Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1529@events.ncbj.gov.pl
DESCRIPTION:Speakers: Roman Shopa (National Centre for Nuclear Research)\n
 We present one of the first images for an in vivo scan of a human patient\
 , measured by the modular Jagiellonian positron emission tomographic (J-PE
 T) prototype\, which records 511-keV annihilation photons via Compton scat
 tering in plastic scintillators [1]. The original reconstruction algorithm
  is adapted from the maximum likelihood expectation maximisation (MLEM)\, 
 with the realistic J-PET system matrix modelling\, time-of-flight (TOF) in
 formation and attenuation and scatter correction applied [2].\n\nThe atten
 uation map of the patient was measured by a CT scan. The scatter factors w
 ere estimated by the single scatter simulation (SSS)\, implemented in the 
 STIR software [3]. The subsampled SSS-sinogram was acquired using the know
 n attenuation factors and a prior MLEM reconstruction\, made without addit
 ive corrections and later upscaled by interpolation. As a result\, a signi
 ficant improvement was achieved in noise suppression and resolution recove
 ry for the reconstructed PET image.\n\n[1] Moskal P et al. MedRxiv 2024.02
 .01.23299028 (2024)\n[2] Shopa RY et al. IEEE TRPMS 7 509 (2023)\n[3] Thie
 lemans K et al. PMB 57 867 (2012)\n\nhttps://events.ncbj.gov.pl/event/314/
 contributions/1529/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1529/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Preliminary study on artificial intelligence methods for cybersecu
 rity threat detection in computer networks based on raw data packets
DTSTART;VALUE=DATE-TIME:20240605T115500Z
DTEND;VALUE=DATE-TIME:20240605T122000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1533@events.ncbj.gov.pl
DESCRIPTION:Speakers: Aleksander Ogonowski (National Centre for Nuclear Re
 search)\, Michał Żebrowski (National Centre for Nuclear Research)\nMost 
 of the methods of the intrusion detection systems for cybersecurity threat
 s detection in computer networks are based on traffic flow characteristics
 . However\, this approach may not fully exploit the potential of deep lear
 ning algorithms to directly extract features from raw packets. Moreover\, 
 it impedes real-time monitoring due to the necessity of waiting for the pr
 ocessing pipeline to complete and introduces dependencies on additional so
 ftware components.\n\nIn this paper\, we investigate deep learning methodo
 logies capable of detecting attacks in real-time directly from raw packet 
 data within network traffic. Our investigation utilizes the CICIDS2017 dat
 aset\, which includes both benign traffic and prevalent real-world attacks
 \, providing a comprehensive foundation for our research.\n\nhttps://event
 s.ncbj.gov.pl/event/314/contributions/1533/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1533/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Developing Artificial Intelligence in the Cloud: the AI_INFN platf
 orm
DTSTART;VALUE=DATE-TIME:20240605T094000Z
DTEND;VALUE=DATE-TIME:20240605T100500Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1497@events.ncbj.gov.pl
DESCRIPTION:Speakers: Rosa Petrini (INFN)\nThe INFN CSN5-funded project AI
 _INFN ("Artificial Intelligence at INFN") aims at fostering the adoption o
 f ML and AI within INFN by providing support on multiple aspects\, includi
 ng the provision of state-of-the-art hardware for AI and ML\, leveraging o
 n cloud native solutions in the context of INFN Cloud\, to share hardware 
 accelerators as effectively as possible without compromising on the divers
 ity of the research activities of the Institute. AI_INFN evolves the Virtu
 al-Machine-based model towards a more flexible platform built on top of Ku
 bernetes. This is meant to be a composable toolkit and currently features:
  JWT-based authentication\, JupyterHub multitenant interface\, distributed
  filesystem\, customizable conda environments\, and a specialized monitori
 ng and accounting system. Last but not least\, the platform is an enabler 
 to implement the offloading mechanism based on Virtual Kubelet and interLi
 nk API\, a synergy with InterTwin. Preliminary results and applications wi
 ll be presented.\n\nhttps://events.ncbj.gov.pl/event/314/contributions/149
 7/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1497/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Up-scaling for measuring the spatial distribution of radiation dos
 e for applications in the preparation of individual patient treatment plan
 s
DTSTART;VALUE=DATE-TIME:20240605T080500Z
DTEND;VALUE=DATE-TIME:20240605T083000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1500@events.ncbj.gov.pl
DESCRIPTION:Speakers: Bartłomiej Rachwał (AGH University of Kraków)\nTh
 e super-resolution (SR) techniques are often used in the up-scaling proces
 s to add-in details that are not present in the original low-resolution im
 age. In radiation therapy the SR can be applied to enhance the quality of 
 medical images used in treatment planning. The Dose3D detector measuring s
 patial dose distribution [1]\, the dedicated set of ML algorithms for SR h
 as been proposed to perform final dose distribution up-scaling. As the SR 
 technique\, the SRCNN [2] architecture has been adjusted. The training and
  validation data being produced with MC simulation with two different scor
 ing resolutions. Extra features related to the beam shape have been define
 d. The input data resolution is the one coming from the measurement (1cc) 
 and the target data resolution is defined at the level of the CT image. Ou
 r research's latest breakthroughs and advancements will feature at the con
 ference.\nReferences: \n[1] https://dose3d.fis.agh.edu.pl\, \n[2] https://
 doi.org/10.1007/978-3-319-10593-2_13\n\nhttps://events.ncbj.gov.pl/event/3
 14/contributions/1500/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1500/
END:VEVENT
BEGIN:VEVENT
SUMMARY:GGEMS - GPU Geant4-based Monte Carlo Simulations
DTSTART;VALUE=DATE-TIME:20240605T074000Z
DTEND;VALUE=DATE-TIME:20240605T080500Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1502@events.ncbj.gov.pl
DESCRIPTION:Speakers: Didier BENOIT ()\nIn medical physics\, GPU-based Mon
 te Carlo simulations (MCS) have been proposed for computational gains. How
 ever\, they remain limited to specific applications and are not easily gen
 eralized.\nGGEMS (GPU Geant4-based Monte Carlo Simulations) is advanced MC
 S software that uses OpenCL. Entirely written in C++\, its software archit
 ecture allows flexibility and generality for numerous applications such as
  imaging and radiation therapy. It has been validated on architectures inc
 luding NVIDIA and Intel graphics cards\, as well as multi-core Intel proce
 ssors on both Windows and Linux. A Python interface is provided for script
 ing\, and an OpenGL graphical interface has been developed to assist users
 .\nGGEMS was evaluated through various medical applications\, demonstratin
 g fast simulation. For example\, for a CT projection simulating 10^9 parti
 cles\, the computation times were: 112s on GeForce 1050Ti\, 385s on Quadro
  P400\, 421s on Xeon 16 threads\, and 91s on 1050Ti+P400.\n\nhttps://event
 s.ncbj.gov.pl/event/314/contributions/1502/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1502/
END:VEVENT
BEGIN:VEVENT
SUMMARY:LLM-based physics analysis agent at BESIII and exploration of futu
 re AI scientist
DTSTART;VALUE=DATE-TIME:20240604T141500Z
DTEND;VALUE=DATE-TIME:20240604T144000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1504@events.ncbj.gov.pl
DESCRIPTION:Speakers: Ke Li (Institute of High Energy Physics\, China)\, Z
 hengde Zhang (Institute of High Energy Physics\, China)\, Yiyu Zhang (Inst
 itute of High Energy Physics\, China)\nThe data processing and analyzing i
 s one of the main challenges at HEP experiments\, normally one physics res
 ult can take more than 3 years to be conducted. To accelerate the physics 
 analysis and drive new physics discovery\, the rapidly developing Large La
 nguage Model (LLM) is the most promising approach\, it have demonstrated a
 stonishing capabilities in recognition and generation of text while most p
 arts of physics analysis can be benefitted. In this talk we will discuss t
 he construction of a dedicated intelligent agent\, an AI assistant at BESI
 II based on LLM\, the potential usage to boost hadron spectroscopy study\,
  and the future plan towards a AI scientist.\n\nhttps://cern.zoom.us/j/679
 24643443?pwd=oHCoX0bnlWFwWq9f1AmnKa1ckQMGGB.1\n\nhttps://events.ncbj.gov.p
 l/event/314/contributions/1504/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1504/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Fast simulation of the Zero Degree Calorimeter responses with gene
 rative neural networks
DTSTART;VALUE=DATE-TIME:20240604T132000Z
DTEND;VALUE=DATE-TIME:20240604T134500Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1505@events.ncbj.gov.pl
DESCRIPTION:Speakers: Maksymilian Wojnar (AGH University of Krakow)\, Emil
 ia Majerz (AGH University of Krakow)\nApplying machine learning methods to
  high-energy physics simulations has recently emerged as a rapidly develop
 ing area. A prominent example is the Zero Degree Calorimeter (ZDC) simulat
 ion in the ALICE experiment at CERN\, where substituting the traditional c
 omputationally extensive Monte Carlo methods with generative models radica
 lly reduces computation time. Although numerous studies have addressed the
  fast ZDC simulation\, there remains significant potential for innovations
 . Recent developments in generative neural networks have enabled the creat
 ion of models capable of producing high-quality samples indistinguishable 
 from real data. In this paper\, we apply the latest advances to the simula
 tion of the ZDC neutron detector and highlight the potential benefits and 
 challenges. Our focus is on exploring novel architectures and state-of-the
 -art generative frameworks. We compare their performance against establish
 ed methods\, demonstrating competitive outcomes in speed and efficiency.\n
 \nhttps://events.ncbj.gov.pl/event/314/contributions/1505/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1505/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Deep Generative Models for Particle Simulations at ALICE\, CERN
DTSTART;VALUE=DATE-TIME:20240604T124000Z
DTEND;VALUE=DATE-TIME:20240604T132000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1526@events.ncbj.gov.pl
DESCRIPTION:Speakers: Patryk Będkowski (Warsaw University of Technology)\
 , Karol Rogoziński (Warsaw University of Technology)\, Mikołaj Kita (War
 saw University of Technology)\nAt the European Organisation for Nuclear Re
 search (CERN)\, scientists study the fundamental properties of matter by r
 eplicating the extreme conditions of the early universe within the Large H
 adron Collider (LHC). Understanding particle collisions requires running s
 imulations that mirror the detectors' expected responses within the LHC. W
 ith over 50% of CERN's GRID computing power dedicated to High Energy Physi
 cs simulations\, the need for more efficient simulation methods is critica
 l.\n\nWe propose employing generative machine learning to directly simulat
 e detector responses\, leveraging advancements in generative adversarial n
 etworks (GANs)\, autoencoders\, and diffusion models to tackle simulation 
 challenges. Our contributions include introducing a modified GAN training 
 objective that accommodates varying simulation variance across different c
 onditional inputs\, supplemented with additional regularization to increas
 e the simulation fidelity. For autoencoders\, we introduce a conditional c
 ontrol mechanism enhancing simulation control by independently manipulatin
 g output parameters of the generated samples. With diffusion models\, we e
 xplore the efficiency of latent diffusion models and the trade-off between
  inference time and simulation quality.\n\nOur proposed methodologies have
  the potential to advance particle collision simulations by offering more 
 streamlined\, controllable\, and faster methods\, maintaining the fidelity
  demanded by modern high-energy physics experiments.\n\nhttps://events.ncb
 j.gov.pl/event/314/contributions/1526/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1526/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Machine learning in HEP
DTSTART;VALUE=DATE-TIME:20240604T120000Z
DTEND;VALUE=DATE-TIME:20240604T124000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1525@events.ncbj.gov.pl
DESCRIPTION:Speakers: Artur Kalinowski (University of Warsaw)\nI will reca
 ll a basic idea behind Machine Learning\, then I will bring random example
 s of ML applications in High Energy Physics.\n\nhttps://events.ncbj.gov.pl
 /event/314/contributions/1525/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1525/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Quantum computing in the service of satellite data processing
DTSTART;VALUE=DATE-TIME:20240604T100500Z
DTEND;VALUE=DATE-TIME:20240604T103000Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1524@events.ncbj.gov.pl
DESCRIPTION:Speakers: Piotr Gawron (AstroCeNT / Nicolaus Copernicus Astron
 omical Center of the Polish Academy of Sciences)\nEarth observation data a
 re constantly being produced by constantly growing number of satellites. P
 rocessing these data efficiently consists a major challenge and not all th
 e produced data is processed and analyzed. At the same time Earth observat
 ion provides important information about our ecosystems in the age of rapi
 dly changing climate. For this reason research on application of quantum c
 omputing for Earth observation data analysis has been initiated be a coupl
 e of research institutions. For me personally participation in this field 
 allows me to study how one can apply a variety of quantum algorithmic tech
 niques to image processing and to join efforts aiming at reducing the impa
 ct of climate change. I will present a short review of ideas and activitie
 s that aim at finding\, possibly impactful\, new methods of satellite data
  processing using quantum computing techniques.\n\nhttps://events.ncbj.gov
 .pl/event/314/contributions/1524/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1524/
END:VEVENT
BEGIN:VEVENT
SUMMARY:AI in Space: Ready for Prime Time?
DTSTART;VALUE=DATE-TIME:20240604T092500Z
DTEND;VALUE=DATE-TIME:20240604T100500Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1523@events.ncbj.gov.pl
DESCRIPTION:Speakers: Jakub Nalepa (Silesian University of Technology/KP L
 abs)\nExciting advancements in remote sensing\, AI\, and edge computing ar
 e transforming scientific and industrial sectors via in-orbit data process
 ing. This technology enables real-time applications such as environmental 
 monitoring\, precision agriculture\, disaster detection\, and in-orbit ano
 maly detection from telemetry data. Integrating AI into space-based system
 s and edge devices swiftly converts raw data\, like multi- or hyperspectra
 l images\, into actionable insights on board satellites. Challenges remain
 \, including hardware limitations\, model validation\, and sparse ground-t
 ruth datasets. In this talk\, we will explore concrete opportunities\, cha
 llenges and solutions related to deploying AI in space\, focusing on Earth
  observation and anomaly detection from satellite telemetry data. The real
  satellite missions\, including OPS-SAT by European Space Agency and Intui
 tion-1 by KP Labs will serve as real-world examples. Finally\, we will dis
 cuss the most exciting research and development avenues in on-board and on
 -ground (quantum) AI for space applications. Fasten your seatbelts\, we ar
 e ready to take off.\n\nhttps://events.ncbj.gov.pl/event/314/contributions
 /1523/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1523/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Machine learning vs. network science: A comparison of two paradigm
 s for the interpretation of high-throughput data in biology and medicine
DTSTART;VALUE=DATE-TIME:20240604T082500Z
DTEND;VALUE=DATE-TIME:20240604T090500Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1520@events.ncbj.gov.pl
DESCRIPTION:Speakers: Marc Hütt (Constructor University)\nOver the last d
 ecades biology and medicine have become data sciences. High-throughput ('o
 mics') data on the level of gene expression\, metabolic activity\, epigene
 tic regulation and others now serve as a prominent source of systemic info
 rmation. This makes these fields accessible to data-driven computational m
 ethods\, in particular *network science* and *machine learning*. \n\n*Netw
 ork science* employs the formal view of graph theory to understand the des
 ign principles of complex systems. Abstracting cellular processes (gene re
 gulation\, metabolism\, protein interactions) into networks has revolution
 ized the way we think about biological systems. \n\n*Machine learning* is 
 most prominent in biological and medical research via the successes of ima
 ge analysis and of protein structure prediction via AlphaFold. Attempts to
  train machine learning devices to interpret 'omics' data has been less su
 ccessful so far. \n\nFocusing on gene expression data as the most common e
 xample (beyond the genome) of 'omics' data\, we discuss possible reasons f
 or the limited success of machine learning in biology and medicine. We sta
 rt with a (deceptively) simple biological situation\, bacterial gene regul
 ation\, and then move to the analysis of medical data.\n\nhttps://events.n
 cbj.gov.pl/event/314/contributions/1520/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1520/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Welcome from the organizers
DTSTART;VALUE=DATE-TIME:20240604T081500Z
DTEND;VALUE=DATE-TIME:20240604T082500Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1522@events.ncbj.gov.pl
DESCRIPTION:Speakers: Wojciech Krzemien (NCBJ)\nShort communication from t
 he workshop organizers\n\nhttps://events.ncbj.gov.pl/event/314/contributio
 ns/1522/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1522/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Welcome address
DTSTART;VALUE=DATE-TIME:20240604T080000Z
DTEND;VALUE=DATE-TIME:20240604T081500Z
DTSTAMP;VALUE=DATE-TIME:20260309T062156Z
UID:indico-contribution-314-1521@events.ncbj.gov.pl
DESCRIPTION:Speakers: Agnieszka Pollo (National Centre for Nuclear Researc
 h AND Jagiellonian University)\nA welcome addess from Professor Agnieszka 
 Pollo\n\nhttps://events.ncbj.gov.pl/event/314/contributions/1521/
LOCATION:
URL:https://events.ncbj.gov.pl/event/314/contributions/1521/
END:VEVENT
END:VCALENDAR