Testing the number of parameters with multidimensional MLP

Joseph Rynkiewicz (1, 2)

1 SAMOS - Statistique Appliquée et MOdélisation Stochastique
2 MATISSE - UMR 8595 - Modélisation Appliquée, Trajectoires Institutionnelles et Stratégies Socio-Économiques

This work concerns testing the number of parameters in one hidden layer multilayer perceptron (MLP). For this purpose we assume that we have identifiable models, up to a finite group of transformations on the weights, this is for example the case when the number of hidden units is know. In this framework, we show that we get a simple asymptotic distribution, if we use the logarithm of the determinant of the empirical error covariance matrix as cost function.

Domaines: Statistiques [math.ST]; Théorie [stat.TH]; Machine Learning [stat.ML]

Joseph Rynkiewicz. Testing the number of parameters with multidimensional MLP. ASMDA 2005, 2005, Brest, France. pp.561-568. ⟨hal-00258206⟩