FEEDFORWARD NEURAL STRUCTURES IN BINARY HYPOTHESIS-TESTING

被引：4

作者：

BATALAMA, SN

KOYIANTIS, AG

PAPANTONIKAZAKOS, P

KAZAKOS, D

机构：

[1] Department of Electrical Engineering, University of Virginia, Charlottesville

来源：

IEEE TRANSACTIONS ON COMMUNICATIONS | 1993年 / 41卷 / 07期

基金：

美国国家科学基金会;

关键词：

D O I：

10.1109/26.231936

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this paper, two feedforward neural structures are considered, whose objective is binary hypothesis testing. The first structure, named FFS1, is a tandem structure, while the second structure, named FFS2, involves cumulative feedforward feedback. Both parametric and robust designs for the two structures are considered and analyzed in terms of induced false alarm and power probabilities. The inferiority of the FFS1 is rigorously proven in terms of the rate with which the induced power probability increases with respect to the number of the neural elements. Asymptotic results are presented, as well as numerical results, with emphasis on the Gaussian and location parameternominal hypotheses model. Learning algorithms for the parameters involved in the robust network designs are discussed as well.

引用

页码：1047 / 1062

页数：16