Back to Search
Start Over
Estimation consistante de l'architecture des perceptrons multicouches
- Source :
-
Comptes Rendus. Mathématique . May2006, Vol. 342 Issue 9, p697-700. 4p. - Publication Year :
- 2006
-
Abstract
- Abstract: We consider regression models involving multilayer perceptrons (MLP) with one hidden layer and Gaussian noise. The estimation of the parameters of the MLP can be made by maximizing the likelihood of the model. In this framework, it is difficult to determine the true number of hidden units because the information matrix of Fisher is not invertible if this number is overestimated. However, if the parameters of the MLP are in a compact set, we prove that the minimization of a suitable information criteria leads to consistent estimation of the true number of hidden units. To cite this article: J. Rynkiewicz, C. R. Acad. Sci. Paris, Ser. I 342 (2006). [Copyright &y& Elsevier]
Details
- Language :
- French
- ISSN :
- 1631073X
- Volume :
- 342
- Issue :
- 9
- Database :
- Academic Search Index
- Journal :
- Comptes Rendus. Mathématique
- Publication Type :
- Academic Journal
- Accession number :
- 20554658
- Full Text :
- https://doi.org/10.1016/j.crma.2006.03.007