A Universal Learning Rule that Minimizes Well-formed Cost Functions

Fecha

2009-07-29T13:59:17Z

Título de la revista

ISSN de la revista

Título del volumen

Editor

Citas

plumx
0 citas en WOS
0 citas en

Resumen

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.

Descripción

Palabras clave

Citación