Layered perceptron versus Neyman-Pearson optimal detection
Cagdas Bas, Robert J. Marks · 1991
A layered perceptron artificial neural network (ANN) is trained to detect positive signals corrupted with noise which, for the present test, is Laplacian. Comparison of the ANN performance is made with both Neyman-Pearson optimal and linear detectors. The ANN invariably outperforms the linear detector and is shown to be nearly optimal. The optimal detector requires knowledge of signal and noise parameters; the ANN does not.>