RESULTS OF USING AN ARTIFICIAL NEURAL-NETWORK TO DISTINGUISH SINGLE ECHOES FROM MULTIPLE SONAR ECHOES

Empirical results illustrate the pitfalls of applying an artificial neural network (ANN) to classifying underwater active sonar returns. During training, a back propagation ANN classifier ''learns'' to recognize two classes of reflected active sonar waveforms. Waveforms in class 1 have two major sonar echoes or peaks. Waveforms in class 2 have one major echo or peak. Our results show how the classifier ''learns'' to distinguish between the two classes. Testing the ANN classifier with different waveforms having one major peak, and waveforms having two major peaks generated unexpected results: The number of echo peaks was not the feature used to separate classes.