Title :
Neural network classification: a Bayesian interpretation
Author_Institution :
Dept. of Electr. Eng., Stanford Univ., CA, USA
fDate :
12/1/1990 12:00:00 AM
Abstract :
The relationship between minimizing a mean squared error and finding the optimal Bayesian classifier is reviewed. This provides a theoretical interpretation for the process by which neural networks are used in classification. A number of confidence measures are proposed to evaluate the performance of the neural network classifier within a statistical framework
Keywords :
Bayes methods; error statistics; minimisation; neural nets; Bayesian classifier; Bayesian interpretation; mean squared error; neural network classifier; statistical framework; Bayesian methods; Circuits; Contracts; Hopfield neural networks; Least squares approximation; Network address translation; Neural networks; Probability; Random variables; Space technology;
Journal_Title :
Neural Networks, IEEE Transactions on
