Título de la tesis:
A Universal Learning Rule that Minimizes Well-formed Cost Functions
Autor/es:
Mora Jiménez, Inma - Cid Sueiro, Jesús
Tipo de documento:
Artículo
Universidad:
Universidad Rey Juan Carlos
Departamento:
Idioma:
Castellano
Palabras clave:
Fecha de la defensa:
29-Jul-2009
Notas:
In this paper, we analyze stochastic gradient learning rules for posterior probability estimation using networks with a
single layer of weights and a general nonlinear activation function. We provide necessary and sufficient conditions on the learning rules and the activation function to obtain probability estimates. Also, we extend the concept of well-formed cost function, proposed by Wittner and Denker, to multiclass problems, and we provide
theoretical results showing the advantages of this kind of objective functions....
Valoración:
Clasificación por
