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 three existing convolutional neural networks on four well-known datasets. We furthermore that DCNFIS outperforms state-of-the-art deep fuzzy systems. We then exploit the transparency of fuzzy logic by deriving explanations, in the form of saliency maps, from the fuzzy rules encoded in DCNFIS. We investigate the properties of these explanations in greater depth using the Fashion-MNIST dataset.

翻译：摘要：可解释人工智能领域的一个关键挑战，是算法透明度（即人类能直接理解算法本身，而非依赖事后解释的难易程度）与其准确性之间众所周知的权衡。本文报告了一种新型深度网络的设计，该网络在不牺牲准确性的前提下提升了透明度。通过融合模糊逻辑与深度学习模型，我们设计了一种深度卷积神经模糊推理系统（DCNFIS），并在四个知名数据集上证明，DCNFIS 的性能与三种现有卷积神经网络相当。进一步地，我们展示了 DCNFIS 优于最先进的深度模糊系统。随后，我们利用模糊逻辑的透明度，从编码在 DCNFIS 中的模糊规则中推导出以显著性图形式呈现的解释。我们使用 Fashion-MNIST 数据集对这些解释的属性进行了更深入的探究。