30 September 2019 to 4 October 2019
Montenegro, Budva, Becici
Europe/Podgorica timezone

Session

Machine Learning Algorithms and Big Data Analytics

3 Oct 2019, 09:00
Conference Hall (Montenegro, Budva, Becici)

Conference Hall

Montenegro, Budva, Becici

Splendid Conference & SPA Resort, 85315 Becici, Montenegro Hotel Splendid

Conveners

Machine Learning Algorithms and Big Data Analytics

  • Gennady Ososkov (Joint Institute for Nuclear Research)

Machine Learning Algorithms and Big Data Analytics

  • Petr Zrelov (LIT JINR)

Presentation materials

There are no materials yet.

  1. Dr Dmitry Kulyabov (PFUR & JINR)
    03/10/2019, 09:00
    Machine Learning Algorithms and Big Data Analytics
    Sectional
    When considering any method customary to distinguish several structural levels: syntax, semantics, pragmatics. Syntax gives the ability to apply the method in question, semantics helps set tasks, and pragmatics answers the questions: what is the essence method, what is the place of the method among other methods. In this paper, the authors apply this approach to the consideration of thedeep...
    Go to contribution page
  2. Dr Alexander Kryukov (SINP MSU)
    03/10/2019, 09:15
    Machine Learning Algorithms and Big Data Analytics
    Sectional
    The method of artificial neural networks is a modern powerful tool for solving various problems for which it is difficult to propose well-formalized solutions. These tasks are various aspects of image analysis. This paper describes the use of convolutional neural networks (CNN) for the problems of classifying the type of primary particles and estimating their energy using images obtained...
    Go to contribution page
  3. Mikhail Titov (Lomonosov Moscow State University)
    03/10/2019, 09:30
    Machine Learning Algorithms and Big Data Analytics
    Sectional
    Interactive visual analysis tools bring the ability of the real-time discovery of knowledge in large and complex datasets using visual analytics. It involves multiple iterations of data processing using various data handling approaches and the efficiency of the whole chain of the analysis process depends on the performance of chosen techniques and related implementations, as well as the...
    Go to contribution page
  4. Konstantin Androsov (INFN Pisa (Italy))
    03/10/2019, 09:45
    Machine Learning Algorithms and Big Data Analytics
    Sectional
    The reconstruction and identification of tau lepton in semi-leptonic (hereinafter referred to as hadronic decays) are crucial for all analyses with tau leptons in the final state. To discriminate the hadronic decays of tau from all 3 main backgrounds (quark or gluon jets, electrons, and muons), maintaining a low rate of misidentification (below 1%) and at the same time with high efficiency on...
    Go to contribution page
  5. Dr Michele Faucci Giannelli (University of Edinburgh)
    03/10/2019, 10:00
    Machine Learning Algorithms and Big Data Analytics
    Sectional
    We present a Generative-Adversarial Network (GAN) based on convolutional neural networks that are used to simulate the production of pairs of jets at the LHC. The GAN is trained on events generated using MadGraph5 + Pythia8, and Delphes3 fast detector simulation. A number of kinematic distributions both at Monte Carlo truth level and after the detector simulation can be reproduced by the...
    Go to contribution page
  6. Mr Yann Donon (Samara National research University)
    03/10/2019, 10:15
    Machine Learning Algorithms and Big Data Analytics
    Sectional
    Linear accelerators are complex machines potentially confronted with significant downtimes periods due to anomalies and subsequent breakdowns in one or more components. The need for reliable operations of linear accelerators is critical for the spread of this technique in medical environment. At CERN, where LINACs are used for particle research, similar issues are encountered, such as the...
    Go to contribution page
  7. Mr Christopher Kullenberg (JINR)
    03/10/2019, 10:30
    Machine Learning Algorithms and Big Data Analytics
    Sectional
    The NOvA neutrino detector experiment is one of the first High Energy Physics experiments to use neural networks (specifically convolutional neural networks, or CNNs) extensively for its analysis. Results have been published using CNNs to categorize events based on the interaction type, and work is being done to use CNNs to reconstruct other event properties and kinematics. We will present an...
    Go to contribution page
  8. Mr Egor Shchavelev (Saint Petersburg State University)
    03/10/2019, 10:45
    Machine Learning Algorithms and Big Data Analytics
    Sectional
    Particle tracking is a very important part of modern high energy physics experiments. While the data stream from such experiments is increasing day by day, current tracking methods lack the ability to fit these amounts of data. In order to solve this problem, new effective machine learning algorithms are actively developed in the HEP.TrkX project for Large Hadron Collider detector and for the...
    Go to contribution page
  9. Mr Vladislav Vorobyev (MEPhI)
    03/10/2019, 11:00
    Machine Learning Algorithms and Big Data Analytics
    Sectional
    Large-scale coordinate-tracking detector TREK based on multi-wire drift chambers is being developed at the Experimental complex NEVOD in MEPhI to study near-horizontal dense muon bundles generated by ultra-high energy cosmic rays. The total area of the setup is 250 m2. The main goal of the installation is the solution of so-called “muon puzzle” – observed excess of the number of muons in...
    Go to contribution page
  10. Mr Pavel Goncharov (Sukhoi State Technical University of Gomel, Gomel, Belarus)
    03/10/2019, 11:30
    Machine Learning Algorithms and Big Data Analytics
    Sectional
    We introduce a radically new approach to the particle track reconstruction problem for tracking detectors of HEP experiments. We developed the end-to-end trainable YOLO-like convolutional neural network named Look Once On Tracks (LOOT) which can process the whole event representing it as an image, but instead of three RGB channels, we use, as channels in depth, discretized contents of...
    Go to contribution page
  11. Ms Anna Fatkina (JINR)
    03/10/2019, 11:45
    Machine Learning Algorithms and Big Data Analytics
    Sectional
    GNA is a high-performance fitting framework developed for the data analysis of the neutrino experiments. The framework is based on data flow principles: an experiment model is represented by the computational graph of simple functions as separate nodes that are computed lazily. In this work, we describe the GPU support library for GNA named cuGNA which uses CUDA toolkit. This library is...
    Go to contribution page
  12. Mr Ivan Kadochnikov (JINR)
    03/10/2019, 12:00
    Computations with Hybrid Systems (CPU, GPU, coprocessors)
    Sectional
    For simulating the dynamics of charged particles in electric and magnetic fields a particle-in-cell (PIC) method is often used. In it the position and velocity of each particle or superparticle is tracked, while the charge density and current density necessary to simulate particle interactions are computed on a stationary mesh. Several approaches are availible to integrating the particle...
    Go to contribution page
  13. Mr Ivan Kadochnikov (JINR, PRUE)
    03/10/2019, 12:15
    Machine Learning Algorithms and Big Data Analytics
    Sectional
    Record matching represents a key step in Big Data analysis, especially important to leverage dis-parate large data sources. Methods of probabilistic record linkage provide a good framework to estimate and interpret partial record matches. However, they require combining string distances for the compared records. That is, direct use of probabilistic record linkage requires processing the...
    Go to contribution page
  14. Sergey Belov (Joint Institute for Nuclear Research)
    03/10/2019, 12:30
    Machine Learning Algorithms and Big Data Analytics
    Sectional
    This paper discusses some approaches to the intellectual text analysis in application to automated monitoring of the labour market. The scheme of construction of an analytical system based on Big Data technologies for the labour market is proposed. Were compared the combinations of methods of extracting semantic information about objects and connections between them (for example, from job...
    Go to contribution page
  15. Ms IULIIA GAVRILENKO (Research Assistant, Plekhanov Russian University of Economics, Moscow, Russia)
    03/10/2019, 12:45
    Machine Learning Algorithms and Big Data Analytics
    Sectional
    Modern econometric modeling of macroeconomic processes usually meets certain challenges due to the incompleteness and heterogeneity of the initial information, as well as huge data volumes involved. In the work, on the example of modeling the level of employment in the regions of the Russian Federation was shown the effectiveness of joint using Big Data technologies and automated deployment of...
    Go to contribution page
  16. Andrey Kotov (Institute for Theoretical and Experimental Physics, Joint Institute for Nuclear Research)
    03/10/2019, 13:00
    Machine Learning Algorithms and Big Data Analytics
    Sectional
    Lattice Quantum Chromodynamics (QCD) is a well-established non-perturbative approach to the theory of strong interactions, QCD. It provides a framework for numerical studies of various complex problems of QCD. Such computations are numerically very demanding and require the most powerful modern supercomputers and algorithms. Within this talk, the lattice QCD simulations which are carried out...
    Go to contribution page
  17. Prof. Sergei Nemnyugin (Saint-Petersburg State University)
    03/10/2019, 13:15
    Machine Learning Algorithms and Big Data Analytics
    Sectional
    BM@N (Baryonic Matter at Nuclotron) is an experiment being developed at Joint Institute for Nuclear Research (Dubna, Russia). It is considered the first step towards implementing the fixed target program at NICA accelerating complex (Nuclotron-based Ion Collider fAcillty). One of the important event reconstruction procedure components is the monitoring of the beam trajectory and the vertex...
    Go to contribution page
Building timetable...