Please use this identifier to cite or link to this item:
Title: Optimization of computational complexity of an artificial neural network
Authors: Vershkov, N. A.
Вершков, Н. А.
Kuchukov, V. A.
Кучуков, В. А.
Kuchukova, N. N.
Кучукова, Н. Н.
Kucherov, N. N.
Кучеров, Н. Н.
Shiriaev, E. M.
Ширяев, Е. М.
Keywords: Mathematical transformations;Network layers;Complex networks;Computational complexity;Control systems;Information filtering;Multilayer neural networks
Issue Date: 2021
Publisher: CEUR-WS
Citation: Vershkov N. А., Kuchukov V. A., Kuchukova N. N., Kucherov N. N., Shiriaev E. M. Optimization of computational complexity of an artificial neural network // CEUR Workshop Proceedings. - 2021. - Том 2913. - Стр. 220 - 226
Series/Report no.: CEUR Workshop Proceedings
Abstract: The article deals with the modelling of Artificial Neural Networks as an information transmission system to optimize their computational complexity. The analysis of existing theoretical approaches to optimizing the structure and training of neural networks is carried out. In the process of constructing the model, the well-known problem of isolating a deterministic signal on the background of noise and adapting it to solving the problem of assigning an input implementation to a certain cluster is considered. A layer of neurons is considered as an information transformer with a kernel for solving a certain class of problems: orthogonal transformation, matched filtering, and nonlinear transformation for recognizing the input implementation with a given accuracy. Based on the analysis of the proposed model, it is concluded that it is possible to reduce the number of neurons in the layers of neural network and to reduce the number of features for training the classifier
Appears in Collections:Статьи, проиндексированные в SCOPUS, WOS

Files in This Item:
File SizeFormat 
scopusresults 1824 .pdf466.87 kBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.