DCNFIS: Deep Convolutional Neuro-Fuzzy Inference System

TL;DR

This paper introduces DCNFIS, a deep convolutional neuro-fuzzy inference system that combines fuzzy logic with deep learning to enhance transparency without losing accuracy, outperforming existing fuzzy methods.

Contribution

The paper presents a novel hybrid deep network that integrates fuzzy logic with convolutional neural networks, achieving state-of-the-art fuzzy system performance and improved interpretability.

Findings

DCNFIS matches CNN accuracy on multiple datasets.

DCNFIS outperforms existing fuzzy systems.

Saliency maps derived from fuzzy rules enhance interpretability.

Abstract

A key challenge in eXplainable Artificial Intelligence is the well-known tradeoff between the transparency of an algorithm (i.e., how easily a human can directly understand the algorithm, as opposed to receiving a post-hoc explanation), and its accuracy. We report on the design of a new deep network that achieves improved transparency without sacrificing accuracy. We design a deep convolutional neuro-fuzzy inference system (DCNFIS) by hybridizing fuzzy logic and deep learning models and show that DCNFIS performs as accurately as existing convolutional neural networks on four well-known datasets and 3 famous architectures. Our performance comparison with available fuzzy methods show that DCNFIS is now state-of-the-art fuzzy system and outperforms other shallow and deep fuzzy methods to the best of our knowledge. At the end, we exploit the transparency of fuzzy logic by deriving explanations, in the form of saliency maps, from the fuzzy rules encoded in the network to take benefit of fuzzy logic upon regular deep learning methods. We investigate the properties of these explanations in greater depth using the Fashion-MNIST dataset.