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.
|Name||Report Series SFB "Adaptive Information Systems and Modelling in Economics and Management Science"|
- Report Series SFB \Adaptive Information Systems and Modelling in Economics and Management Science\