Title :
Bounding the performance of neural network estimators, given only a set of training data
Author :
Liang, Weibo ; Manry, Michael T. ; Yu, Qiang ; Apollo, Steven J. ; Dawson, Michael S. ; Fung, Adrian K.
Author_Institution :
Dept. of Electr. Eng., Texas Univ., Arlington, TX, USA
fDate :
31 Oct-2 Nov 1994
Abstract :
Uses a neural network method for obtaining a stochastic Cramer-Rao bound on estimates, given only the training data. The Cramer-Rao bounds can be used (1) to help determine when neural net training should be stopped, (2) to re-order the network inputs according to their contributions to the bounds, and (3) to eliminate less useful inputs. The convergence of the modelling procedure is shown. Examples are provided to illustrate the method
Keywords :
convergence; estimation theory; learning (artificial intelligence); multilayer perceptrons; signal detection; stochastic processes; convergence; modelling procedure; network inputs; neural network estimators; performance; stochastic Cramer-Rao bound; training data; Convergence; Equations; Estimation theory; Maximum likelihood estimation; Multilayer perceptrons; Neural networks; Parameter estimation; Postal services; Stochastic processes; Training data;
Conference_Titel :
Signals, Systems and Computers, 1994. 1994 Conference Record of the Twenty-Eighth Asilomar Conference on
Conference_Location :
Pacific Grove, CA
Print_ISBN :
0-8186-6405-3
DOI :
10.1109/ACSSC.1994.471593
