Title :
A neural network approach to a Bayesian statistical decision problem
Author :
Miyake, Shigeki ; Kanaya, Fumio
Author_Institution :
NTT Transmission Syst. Lab., Kanagawa, Japan
fDate :
9/1/1991 12:00:00 AM
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
Keywords :
Bayes methods; decision theory; neural nets; statistical analysis; Bayesian statistical decision problem; generic loss function; mean-squared error; neural network; objective functions; Backpropagation; Bayesian methods; Loss measurement; Neural networks; Neurons; Pattern recognition; Propagation losses; Robustness; State-space methods; Supervised learning;
Journal_Title :
Neural Networks, IEEE Transactions on
