Título: Priors Stabilizers and Basis Functions: From Regularization to Radial, Tensor and Additive Splines
Autores: Girosi, Federico
Jones, Michael
Poggio, Tomaso
Fecha: 2004-10-20
2004-10-20
1993-06-01
Publicador: MIT
Fuente:
Tipo:
Tema: regularization theory
radial basis functions
additivesmodels
prior knowledge
multilayer perceptrons
Descripción: We had previously shown that regularization principles lead to approximation schemes, as Radial Basis Functions, which are equivalent to networks with one layer of hidden units, called Regularization Networks. In this paper we show that regularization networks encompass a much broader range of approximation schemes, including many of the popular general additive models, Breiman's hinge functions and some forms of Projection Pursuit Regression. In the probabilistic interpretation of regularization, the different classes of basis functions correspond to different classes of prior probabilities on the approximating function spaces, and therefore to different types of smoothness assumptions. In the final part of the paper, we also show a relation between activation functions of the Gaussian and sigmoidal type.
Idioma: Inglés

Artículos similares:

Description Of Procedures In Automotive Engine Plants por Artzner, Denis,Whitney, Dr. Daniel
Reading Courtesy Amounts on Handwritten Paper Checks por Palacios, Rafael,Wang, Patrick S.P.,Gupta, Amar
On Trees and Logs por Pavlova, Anna,Cass, David
Saturn, The GM/UAW Partnership por Rubinstein, Saul,Kochan, Thomas
Academic Earmarks and the Returns to Lobbying por De Figueiredo, John M.,Silverman, Brian S.
10