A NEURAL NETWORK APPROACH TO A BAYESIAN STATISTICAL DECISION PROBLEM

被引：8

作者：

MIYAKE, S

KANAYA, F

机构：

[1] NTT Transmission Systems laboratories, Kanagawa 238-03, 1-2356 Take, Yokosuka-shi

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 1991年 / 2卷 / 05期

关键词：

D O I：

10.1109/72.134293

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This letter proposes generalized mean-squared error (GMSE) objective functions that can be used in neural networks to yield a Bayes optimal solution to a statistical decision problem characterized by a generic loss function.

引用

页码：538 / 540

页数：3