Techniques for biased data distributions and variable classification with neural networks applied to otoneurological data

Abstract

It is frequently useful and advantageous to investigate not only the classification efficacy of neural networks, but also the reasons for misclassification and relations between input variables and output classes. We have developed novel techniques to disentangle these dilemmas: a network structure and learning strategy for biased output class distributions, a method to measure the classification information incorporated in variables and variable groups, and methods to express properties learned by a network from its structure. We tested these techniques with otoneurological data from the conjunction with vertiginous diseases that we have explored in our previous neural network studies.