Stationary and integrated autoregressive neural network processes
We consider autoregressive neural network (ARNN) processes driven by additive noise. Sufficient conditions on the network weights (parameters) are derived for the ergodicity and stationarity of the process. It is shown that essentially the linear part of the ARNN process determines whether the overa...
| Main Authors: | , , |
|---|---|
| Format: | Others |
| Language: | en |
| Published: |
SFB Adaptive Information Systems and Modelling in Economics and Management Science, WU Vienna University of Economics and Business
1998
|
| Subjects: | |
| Online Access: | http://epub.wu.ac.at/302/1/document.pdf |