Robust classification of high-dimensional data using artificial neural networks

Abstract

This paper is concerned with the application of artificial neural networks (ANNs) to a practical, difficult and high-dimensional classification problem, discrimination between selected under-water sounds. The application provides for a particular comparison of the relative performance of time-delay as opposed to fully connected network architectures, in the analysis of temporal data. More originally, suggestions are given for adapting the conventional backpropagation algorithm to give greater robustness to mis-classification errors in the training examples—a particular problem with underwater sound data and one which may arise in other realistic applications of ANNs. An informal comparison is made between the generalisation performance of various architectures in classifying real dolphin sounds when networks are trained using the conventional least squares minimisation norm, L2, that of least absolute deviation, L1, and that of the Huber criterion, which involves a mixture of both L1 and L2. The results suggest that L1 and Huber may provide performance gains. In order to evaluate these ‘robust’ adjustments more formally under controlled conditions, an experiment is then conducted using simulated dolphin sounds with known levels of random noise and misclassification error. Here, the results are more ambiguous and significant interactions are indicated which raise issues for future research.