Open AccessNeural network-based models of binomial time series in data analysis problems
Author(s) -
Yu. S. Kharin
Publication year - 2021
Publication title -
doklady nacionalʹnoj akademii nauk belarusi
Language(s) - English
Resource type - Journals
eISSN - 2524-2431
pISSN - 1561-8323
DOI - 10.29235/1561-8323-2021-65-6-654-660
Subject(s) - series (stratigraphy) , artificial neural network , time series , estimator , computer science , algorithm , negative binomial distribution , ergodicity , equivalence (formal languages) , mathematics , data mining , artificial intelligence , machine learning , statistics , poisson distribution , discrete mathematics , paleontology , biology
This article is devoted to constructing neural network-based models for discrete-valued time series and their use in computer data analysis. A new family of binomial time series based on neural networks is presented, which makes it possible to approximate the arbitrary-type stochastic dependence in time series. Ergodicity conditions and an equivalence relation for these models are determined. Consistent statistical estimators for model parameters and algorithms for computer data analysis (including forecasting and pattern recognition) are developed.