• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Student
Title
Supervisor
Faculty
Educational Programme
Final Grade
Year of Graduation
Anastasiya Demidova
Construction of a generative neural network for simulation of electromagnetic showers.
2019
Data modeling and analysis is an essential part of experiments in high energy physics. Monte-Carlo simulation is used to interpret experimental results and evaluate performance but is the most computationally expensive part of the experiment. One of the most computationally expensive tasks is the simulation of electromagnetic showers in nuclear photoemulsion detectors. Similar track detectors in high energy physics are used to detect and measure particle energy.

In this work, an alternative method for simulating electromagnetic showers based on generative neural networks is proposed. Electromagnetic shower can be represented as a graph in order to preserve the history of the interaction between tracks. In this regard, the task of generation of electromagnetic showers consists of two parts: generating the graph structure and the generation of characteristics of the vertices. The graph structure is generated using the GrphRNN approach, which models the graph using a recurrent network as a sequence of vertices and a sequence of edges for each new vertex. To generate features of graph vertices, a generative adversarial network is used, where the generator and discriminator architecture consists of graph convolutional networks.

The proposed approach makes it possible to generate electromagnetic showers similar in structure to real showers, but poorly captures the branching of the shower.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses