Accession Number : ADA247724

Title :   Computer Assisted Improvement of the Estimation Mean Squared Error with Application to Back Propagation Neural Networks.

Descriptive Note : Final rept.,

Corporate Author : NAVAL HEALTH RESEARCH CENTER SAN DIEGO CA

Personal Author(s) : Angus, J. E.

Report Date : 24 JUL 1991

Pagination or Media Count : 11

Abstract : A computer assisted method for improving the mean squared error (MSE) in estimation for parametric models is presented. Assuming existence of nontrivial sufficient statistics, the method involves generation of Monte Carlo samples from the conditional distribution of the observables, given the sufficient statistic(s). The method is illustrated in connection with a simple back-propagation neural network model for estimating a logistic regression function. Key Words and Phrases: Parametric estimation, exponential families, nonlinear models, nonlinear least squares, neural networks, Monte Carlo simulation, computer intensive statistical methods.

Descriptors :   *ESTIMATES, *COMPUTER APPLICATIONS, *STATISTICAL ANALYSIS, *PARAMETRIC ANALYSIS, COMPUTERS, DISTRIBUTION, FUNCTIONS, LOGISTICS, MEAN, MODELS, NETWORKS, PROPAGATION, SIMULATION, STATISTICS, NEURAL NETS.

Subject Categories : Statistics and Probability

Distribution Statement : APPROVED FOR PUBLIC RELEASE