60167

Автор(ы): 

Автор(ов): 

2

Параметры публикации

Тип публикации: 

Доклад

Название: 

Identification of partially observed subgraphs by deep learning methods in conditions of a priori uncertainty and stochastic disturbances (using the example of the constellation recognition task)

Электронная публикация: 

Да

ISBN/ISSN: 

978-5-209-10386-8

Наименование конференции: 

  • 5th International Conference on Stoсhastic Methods 2020

Наименование источника: 

  • Proceedings of the 5th International Conference on Stochastic Methods (ICSM-5, 2020)

Город: 

  • Москва

Издательство: 

  • РУДН

Год издания: 

2020

Страницы: 

272-276
Аннотация
This work demonstrates the effective capabilities of deep neural networks in solution of the problem of structural identification on graphs in conditions of a priori uncertainty, incomplete observability and stochastic disturbances which is also knows as subgraph detection or recovery. The problem of identification of observed constellations in a photo of the night sky was considered as a test. The solution with quality of 0.927 𝐹1 is obtained. In this work we synthesized original ResNet architecture of the convolution neural network with 26 trainable layers, 415 193 configurable parameters, carried out statistical analysis of structural characteristics of the dataset and adapted the standard binary cross entropy loss function, developed a special strategy for learning the neural network, an adequate criterion of observability of the constellation in the image was formed. We also studied the influence of noise on the quality and stability of the received solutions.

Библиографическая ссылка: 

Галкин В.А., Макаренко А.В. Identification of partially observed subgraphs by deep learning methods in conditions of a priori uncertainty and stochastic disturbances (using the example of the constellation recognition task) / Proceedings of the 5th International Conference on Stochastic Methods (ICSM-5, 2020). М.: РУДН, 2020. С. 272-276.