Title :
On the identification of recurrent neural nets
Author :
Trummer, Dietmar ; Deistler, Manfred
Author_Institution :
Inst. of Econometrics, Oper. Res. & Syst. Theory, Wien Univ. of Technol., Austria
Abstract :
Observational equivalence for so-called Jordan networks, which are a special class of recurrent networks, is analysed. We show this type of neural nets to belong to a wider class of mixed networks and use the description of observational equivalence available for the latter class for obtaining the respective results for the first class
Keywords :
identification; matrix algebra; recurrent neural nets; Jordan networks; mixed networks; observational equivalence; Econometrics; Feeds; Neural networks; Nonlinear systems; Operations research; Recurrent neural networks; Speech recognition; State estimation; Yttrium;
Conference_Titel :
Decision and Control, 2000. Proceedings of the 39th IEEE Conference on
Conference_Location :
Sydney, NSW
Print_ISBN :
0-7803-6638-7
DOI :
10.1109/CDC.2000.912156
