A neural network approach to a Bayesian statistical decision problem

S Miyake; F Kanaya

doi:10.1109/72.134293

A neural network approach to a Bayesian statistical decision problem

IEEE Trans Neural Netw. 1991;2(5):538-40. doi: 10.1109/72.134293.

Authors

S Miyake¹, F Kanaya

Affiliation

¹ NTT Transmission Syst. Lab., Kanagawa.

PMID: 18282869
DOI: 10.1109/72.134293

Abstract

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