FEATURES OF MODELING IN VARIOUS TYPES OF NEURAL NETWORKS

UDC 004.032.26
DOI: 10.36871/2618-9976.2022.03.005

Authors

Zvyagin L.S.
PhD of Economics, Associate Professor, Financial University under the Government of the Russian Federation, Associate Professor of the Department "System analysis in economics", Moscow, Russia

Abstract

Currently, the IT market uses the term "machine learning" as a direction of scientific engineering, closely related to the development of algorithms for training artificial neural networks based on data from various sensors or databases. The main principle of machine learning is selftraining of a neural network to patterns and making reasonable decisions by analyzing the data obtained. Consequently, machine learning is closely related to areas such as statistics, data mining, pattern recognition, and artificial intelligence. Neural networks are a popular platform for machine learning, but there are many other machine learning methods, such as logistic regression and auxiliary vector machines.

Keywords

Neural networks, Information systems, Modeling, Analysis, Processes and algorithms, Artificial intelligence, Big data