Article 3421

Title of the article

MATHEMATICAL MODEL OF AN ARTIFICIAL NEURAL NETWORK FOR SOLVING DATA MINING PROBLEMS 

Authors

Amandos D. Tulegulov, Candidate of physical and mathematical sciences, associate professor, head of the sub-department of aviation engineering and technology, Academy of Civil Aviation (44 Akhmetova street, Almaty, Kazakhstan), E-mail: tad62@yandex.kz
Dastan S. Ergaliev, Ph.D., associate professor, professor of the sub-department of aviation engineering and technology, Academy of Civil Aviation (44 Akhmetova street, Almaty, Kazakhstan), E-mail: DES-67@yandex.kz
Saltanat Zh. Kenbeilova, PhD, scientific secretary, Academy of Civil Aviation (44 Akhmetova street, Almaty, Kazakhstan), E-mail: sal-japaspai@mail.ru
Asylkhan Ismailov, Master degree student, Kazakh University of Technology and Business (37A Kayim Mukhamedkhanova street, Nur-Sultan, Kazakhstan), E-mail: Asyl@mail.ru
Karshyga M. Akishev, Senior lecturer of the sub-department of information technologies, Kazakh University of Technology and Business (37A Kayim Mukhamedkhanova street, Nur-Sultan, Kazakhstan), E-mail: tad62@ya.ru 

Index UDK

004.838.2 

DOI

10.21685/2307-4205-2021-4-3 

Abstract

Background. The article discusses a neural network (artificial neural network) as a kind of mathematical model. Also, the work analyzes its software and hardware implementation. Materials and methods. The neural network method is associated with deep learning. The proposed model is built on the principle of organization and functioning of biological neural networks – networks of nerve cells of a living organism. It is a system of interconnected and interacting simple processors in the form of artificial neurons. When connected in a large network with controlled interactions, these simple processors taken separately are capable of performing quite complex tasks together. Results. As a result of the research carried out, ensemble methods can be noted, which are a method of intellectual learning, where several models are trained to solve a single question posed and are combined to obtain the best results. The main assumption of the application of the method: with the right combination of weak models, more reliable and accurate results can be achieved. Conclusions. The described ensemble machine learning methods are so-called metaalgorithms that combine several machine learning methods into one predictive model. These algorithms consist of two steps: creating a distribution of simple ML models over subsets of the original data and combining the distribution into one "aggregated" model. 

Key words

neural network, mathematical model, hardware implementation, processor, tasks 

Download PDF

 

Дата создания: 16.02.2022 13:07
Дата обновления: 16.02.2022 13:27