Interpretable Convolutional Neural Networks Using a Rule-Based Framework for Classification

Abstract

A convolutional neural network (CNN) learning structure is proposed, with added interpretability-oriented layers, in the form of Fuzzy Logic-based rules. This is achieved by creating a classification layer based on a Neural Fuzzy classifier, and integrating it into the overall learning mechanism within the deep learning structure. Using this new structure, one can extract linguistic Fuzzy Logic-based rules from the deep learning structure directly, and link this information to input features, which enhances the interpretability of the overall system. The classification layer is realised via a Radial Basis Function (RBF) Neural-Network, that is a direct equivalent of a class of Fuzzy Logic-based systems. In this work, the development of the RBF neural-fuzzy system and its integration into the deep-learning CNN is presented. The proposed hybrid CNN RBF-NF structure can form a fundamental building block, towards building more complex deep-learning structures with Fuzzy Logic-based interpretability. Using simulation results on benchmark data (MNIST handwriting digits and MNIST Fashion) we show that the proposed learning structure maintains a good level of forecasting/prediction accuracy compared to CNN deep learning structures. Crucially, we also demonstrate in both cases the resulting interpretability, in the form of linguistic rules that link the classification decisions to the input feature space.