A universal learning rule that minimizes well-formed cost functions |
| |
Authors: | Mora-Jimenez I Cid-Sueiro J |
| |
Affiliation: | Dept. of Signal Theor. & Commun., Univ. Carlos III de Madrid, Leganes-Madrid, Spain; |
| |
Abstract: | 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. |
| |
Keywords: | |
|
|