Abstract
Often, Neural Networks are involved in binary detectors of communication, radar or sonar systems. The design phase of a neural network detector usually requires the application of Monte Carlo trials in order to estimate some performance parameters.
The classical Monte Carlo method is suitable to estimate high event probabilities (higher than 0.01), but not suitable to estimate very low event probabilities (say, 10−5 or less). For estimations of very low false alarm probabilities (or error probabilities), a modified Monte Carlo technique, the so-called Importance Sampling (IS) technique, is considered in this paper; some topics are developed, such as optimal and suboptimal IS probability density functions (biasing density functions), control parameters and new algorithms for the minimization of the estimator error.
The main novelty of this paper is the application of an efficient IS technique on neural networks, drastically reducing the number of patterns required for testing events of low probability. As a practical application, the IS technique is applied to a neural detector on a radar (or sonar) system.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
K.S. Shanmugam and P. Balaban, “A modified Monte Carlo simulationtechnique for the evaluation of error rate in digital communication systems, ” IEEE Trans. Commun., Vol. COM-28, pp. 1916–1924, Nov. 1980.
D. Lu and K. Yao, “Improvedimportance sampling technique for efficient simulation of digital communication systems, ” IEEE J. Select. Areas Commun., Vol. SAC-6, pp. 67–75, Jan. 1988.
R.J. Wolfe, M.C. Jeruchim and P.M. Hahn, “On optimum and suboptimum biasing procedures for importance sampling in communication simulation, ” IEEE Trans. Commun., Vol. COM-38, pp. 639–647, May 1990.
J.C. Chen, D. Lu, J.S. Sadowsky and K. Yao, “On importance sampling in digitalcommunications - Part I: Fundamentals, ” IEEE J. Select. Areas Commun., Vol. SAC-11, pp. 289–299, Apr. 1993.
G.C. Orsak, “A note on estimating false alarm rates via importancesampling, ” IEEE Trans. Commun., Vol. COM-41, pp. 1275–1277, Sept. 1993.
J.S. Stadler and S. Roy, “Importance sampling for detection of scale problems” IEEE Trans. Commun., Vol. COM-43, pp. 2862–2865, Dec. 1995.
M. Devetsikiotis and J.K. Townsend, “An algorithmic approach to the optimization of importance sampling parameters in digital communication system simulation, ” IEEE Trans. Commun., Vol. COM-41, pp. 1464–1473, Oct. 1993.
D. Andina and J.L. Sanz-González. “On the problem of binary detection withNeural Networks”, Proc. 38th Midwest Symposium on Circuit and Systems, MSCS'95, pp. 554–557, Rio de Janeiro, Brazil, August 1995.
D. Andina, J.L. Sanz-González and A. Jiménez-Pajares, “A comparison of criterion functions for a Neural Network applied to binary detection”, Proc. of IEEE Int. Conf. on Neural Networks, ICNN'95, pp. 329–333, Perth, Australia, November, 1995.
A. El-Jaroudi and J. Makhoul, “A new error criterion for posterior probability estimation with Neural Nets”, Proc. of Int. Joint Conf. on Neural Networks, IJCNN2019'90, Vol. I, pp. 185–192, San Diego, CA, 1990.
H.L. Van Trees, “Detection, estimation and modulation theory”, Part I, J. Wiley and Sons: New York, 1968.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Sanz-gonzález, J.L., Andina, D. Performance Analysis of Neural Network Detectors by Importance Sampling Techniques. Neural Processing Letters 9, 257–269 (1999). https://doi.org/10.1023/A:1018612207016
Issue Date:
DOI: https://doi.org/10.1023/A:1018612207016