MATHEMATICAL MODEL OF AN ARTIFICIAL NEURAL NETWORK FOR SOLVING DATA MINING PROBLEMS
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 pr...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penza State University Publishing House
2022-02-01
|
| Series: | Надежность и качество сложных систем |
| Subjects: |
| _version_ | 1818248451090022400 |
|---|---|
| author | A.D. Tulegulov D.S. Ergaliev S.Zh. Kenbeilova A. Ismailov K.M. Akishev |
| author_facet | A.D. Tulegulov D.S. Ergaliev S.Zh. Kenbeilova A. Ismailov K.M. Akishev |
| author_sort | A.D. Tulegulov |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-12T15:20:48Z |
| format | Article |
| id | doaj.art-fce6f2aa791d422a9efdc9cbfbdb233d |
| institution | Directory Open Access Journal |
| issn | 2307-4205 |
| language | English |
| last_indexed | 2024-12-12T15:20:48Z |
| publishDate | 2022-02-01 |
| publisher | Penza State University Publishing House |
| record_format | Article |
| series | Надежность и качество сложных систем |
| spelling | doaj.art-fce6f2aa791d422a9efdc9cbfbdb233d2022-12-22T00:20:24ZengPenza State University Publishing HouseНадежность и качество сложных систем2307-42052022-02-01410.21685/2307-4205-2021-4-3MATHEMATICAL MODEL OF AN ARTIFICIAL NEURAL NETWORK FOR SOLVING DATA MINING PROBLEMSA.D. Tulegulov0D.S. Ergaliev1S.Zh. Kenbeilova2A. Ismailov3K.M. Akishev4Academy of Civil AviationAcademy of Civil AviationAcademy of Civil AviationKazakh University of Technology and BusinessKazakh University of Technology and BusinessBackground. 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.neural networkmathematical modelhardware implementationprocessortasks |
| spellingShingle | A.D. Tulegulov D.S. Ergaliev S.Zh. Kenbeilova A. Ismailov K.M. Akishev MATHEMATICAL MODEL OF AN ARTIFICIAL NEURAL NETWORK FOR SOLVING DATA MINING PROBLEMS Надежность и качество сложных систем neural network mathematical model hardware implementation processor tasks |
| title | MATHEMATICAL MODEL OF AN ARTIFICIAL NEURAL NETWORK FOR SOLVING DATA MINING PROBLEMS |
| title_full | MATHEMATICAL MODEL OF AN ARTIFICIAL NEURAL NETWORK FOR SOLVING DATA MINING PROBLEMS |
| title_fullStr | MATHEMATICAL MODEL OF AN ARTIFICIAL NEURAL NETWORK FOR SOLVING DATA MINING PROBLEMS |
| title_full_unstemmed | MATHEMATICAL MODEL OF AN ARTIFICIAL NEURAL NETWORK FOR SOLVING DATA MINING PROBLEMS |
| title_short | MATHEMATICAL MODEL OF AN ARTIFICIAL NEURAL NETWORK FOR SOLVING DATA MINING PROBLEMS |
| title_sort | mathematical model of an artificial neural network for solving data mining problems |
| topic | neural network mathematical model hardware implementation processor tasks |
| work_keys_str_mv | AT adtulegulov mathematicalmodelofanartificialneuralnetworkforsolvingdataminingproblems AT dsergaliev mathematicalmodelofanartificialneuralnetworkforsolvingdataminingproblems AT szhkenbeilova mathematicalmodelofanartificialneuralnetworkforsolvingdataminingproblems AT aismailov mathematicalmodelofanartificialneuralnetworkforsolvingdataminingproblems AT kmakishev mathematicalmodelofanartificialneuralnetworkforsolvingdataminingproblems |