Resource title

On the stationarity of autoregressive neural network models

Resource image

image for OpenScout resource :: On the stationarity of autoregressive neural network models

Resource description

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. (author's abstract) ; Series: Report Series SFB "Adaptive Information Systems and Modelling in Economics and Management Science"

Resource author

Friedrich Leisch, Adrian Trapletti, Kurt Hornik

Resource publisher

Resource publish date

Resource language

en

Resource content type

application/pdf

Resource resource URL

http://epub.wu.ac.at/1612/1/document.pdf

Resource license

Adapt according to the license agreement. Always reference the original source and author.