ROC performance evaluation of multilayer perceptrons in the detection of one of M orthogonal signals
A neural network detector is compared to an optimal algorithm from signal detection theory for the problem of one of M orthogonal signals in a Gaussian noise environment. The neural detector is a multilayer per-ceptron trained with the back-propagation algorithm, while the optimal detector operates based on a likelihood ratio test. It was observed that for the signal-known-exactly case (M = 1) the performance of the neural detector converges to the performance of the ideal Bayesian decision processor; however, for a higher degree of uncertainty (i.e. for a larger M) the performance of the multilayer perceptron is obviously inferior to that of the optimal detector. In addition, it was concluded that noise information in the training stage affects only slightly the performance of the neural detector. However, the knowledge of the noise distribution proved to be vital for the detection theory processor.
