An Analysis of Artificial Neural Network Pruning Algorithms in Relation to Land Cover Classification Accuracy

Artificial neural networks (ANNs) have been widely used for many classification purposes and generally proved to be more powerful than conventional statistical techniques. However, the use of ANNs requires decisions on the part of the user which may affect the accuracy of the resulting classification. One of these decisions concerns the determination of the optimum network structure for a particular problem. In fact, network structure has a direct effect on the generalisation capabilities of the network. Pruning techniques can be used to reduce network size and thus improve generalisation capabilities. In this study, a feed-forward artificial neural network learning a classification task by backpropagation algorithm was used to classify agricultural crops from microwave SAR and optical SPOT images. Three major pruning algorithms (magnitude based pruning, optimum brain damage, and optimal brain surgeon) were then analysed to find out their performance and visualised to understand their behavior. Results show that these algorithms can be quite effective, even when the number of links in the network is reduced by around 60%. Comparison of the analyses shows that the optimal brain surgeon algorithm is the most effective and reliable method. Overall, pruning techniques appear to have great potential for future studies.