Interpretable Deep Convolutional Fuzzy Classifier

While deep learning has proven to be a powerful new tool for modeling and predicting a wide variety of complex phenomena, those models remain incomprehensible black boxes. This is a critical impediment to the widespread deployment of deep learning technology, as decades of research have found that users simply will not trust (i.e., make decisions based on) a model whose solutions cannot be explained. Fuzzy systems, on the other hand, are by design much more easily understood. In this article, we propose to create more comprehensible deep networks by hybridizing them with fuzzy logic. Our proposed architecture first employs a convolutional neural network as an automated feature extractor and then performs a fuzzy clustering in the derived feature space. After hardening the clusters, we employ Rocchio's algorithm to classify the data points. Experiments on three datasets show that the automated feature extraction substantially improves the accuracy of the fuzzy classifier, and while the substitution of a fuzzy classifier slightly decreases the network's performance, we are able to introduce an effective interpretation mechanism.