Feedforward neural structures in binary hypothesis testing

Two feedforward neural structures intended for binary hypothesis testing are considered. The first structure, FFS1, is a tandem structure, while the second structure, 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 proved 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 parameter nominal hypotheses model. Learning algorithms for the parameter involved in the robust network designs are discussed as well. >

[1]  D. Kazakos,et al.  Fundamental neural structures, operations, and asymptotic performance criteria in decentralized binary hypothesis testing , 1991, [1991 Proceedings] IEEE Conference on Neural Networks for Ocean Engineering.

[2]  D. Kleinman,et al.  Optimization of detection networks. I. Tandem structures , 1990, 1990 IEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings.

[3]  T. Cover.  Hypothesis Testing with Finite Statistics , 1969 .

[4]  Paulo J. G. Lisboa,et al.  Special Issue on Neural Networks , 1993 .

[5]  D. Kazakos,et al.  Neural network structures with feedback, in binary hypothesis testing , 1991, Conference Proceedings 1991 IEEE International Conference on Systems, Man, and Cybernetics.