On the stationarity of autoregressive neural network models

Leisch, Friedrich and Trapletti, Adrian and Hornik, Kurt ORCID: https://orcid.org/0000-0003-4198-9911 (1998) On the stationarity of autoregressive neural network models. Report Series SFB "Adaptive Information Systems and Modelling in Economics and Management Science", 21. SFB Adaptive Information Systems and Modelling in Economics and Management Science, WU Vienna University of Economics and Business, Vienna.

[img]
Preview
PDF
document.pdf

Download (431kB)

Abstract

We analyze the asymptotic behavior of autoregressive neural network (AR-NN) processes using techniques from Markov chains and non-linear time series analysis. It is shown that standard AR-NNs without shortcut connections are asymptotically stationary. If linear shortcut connections are allowed, only the shortcut weights determine whether the overall system is stationary, hence standard conditions for linear AR processes can be used.

Item Type: Paper
Divisions: Departments > Finance, Accounting and Statistics > Statistics and Mathematics
Departments > Informationsverarbeitung u Prozessmanag. > Informationswirtschaft
Departments > Informationsverarbeitung u Prozessmanag. > Produktionsmanagement > Taudes
Departments > Marketing > Service Marketing und Tourismus
Depositing User: Repository Administrator
Date Deposited: 08 Mar 2002 07:57
Last Modified: 24 Oct 2019 13:41
URI: https://epub.wu.ac.at/id/eprint/1612

Actions

View Item View Item

Downloads

Downloads per month over past year

View more statistics