## A note on the identifiability of the conditional expectation for the mixtures of neural networks

• We consider a generalized mixture of nonlinear AR models, a hidden Markov model for which the autoregressive functions are single layer feedforward neural networks. The non trivial problem of identifiability, which is usually postulated for hidden Markov models, is addressed here.

### Additional Services

Author: Jürgen Franke, Jean-Pierre Stockis, Joseph Tadjuidje Kamgaing urn:nbn:de:hbz:386-kluedo-14760 Report in Wirtschaftsmathematik (WIMA Report) (104) Preprint English 2007 2007 Technische Universität Kaiserslautern Identifiability; Mixture Models ; Neural networks Fachbereich Mathematik 510 Mathematik

$Rev: 12793$