The Community for Technology Leaders
Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers (1994)
Pacific Grove, CA, USA
Oct. 31, 1994 to Nov. 2, 1994
ISSN: 1058-6393
ISBN: 0-8186-6405-3
pp: 912-916
Weibo Liang , Dept. of Electr. Eng., Texas Univ., Arlington, TX, USA
M.T. Manry , Dept. of Electr. Eng., Texas Univ., Arlington, TX, USA
Qiang Yu , Dept. of Electr. Eng., Texas Univ., Arlington, TX, USA
S.J. Apollo , Dept. of Electr. Eng., Texas Univ., Arlington, TX, USA
M.S. Dawson , Dept. of Electr. Eng., Texas Univ., Arlington, TX, USA
A.K. Fung , Dept. of Electr. Eng., Texas Univ., Arlington, TX, USA
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.<>
INDEX TERMS
convergence, multilayer perceptrons, estimation theory, stochastic processes, signal detection, learning (artificial intelligence)
CITATION

Weibo Liang, M. Manry, Qiang Yu, S. Apollo, M. Dawson and A. Fung, "Bounding the performance of neural network estimators, given only a set of training data," Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers(ACSSC), Pacific Grove, CA, USA, 1995, pp. 912-916.
doi:10.1109/ACSSC.1994.471593
90 ms
(Ver 3.3 (11022016))