When deep neural networks optimize highly complex functions, it is not always obvious how they reach the final decision. Providing explanations would make this decision process more transparent and improve a user's trust towards the machine as they help develop a better understanding of the rationale behind the network's predictions. Here, we present an explainable observer-classifier framework that exposes the steps taken through the model's decision-making process. Instead of assigning a label to an image in a single step, our model makes iterative binary sub-decisions, which reveal a decision tree as a thought process. In addition, our model allows to hierarchically cluster the data and give each binary decision a semantic meaning. The sequence of binary decisions learned by our model imitates human-annotated attributes. On six benchmark datasets with increasing size and granularity, our model outperforms the decision-tree baseline and generates easy-to-understand binary decision sequences explaining the network's predictions.

本研究提出了一种不妥协预测准确性的情况下融合解释性的决策制定算法，通过学习迭代二进制子决策的方法，在决策过程中引入了稀疏性和透明度。该模型的关键点在于利用神经网络和消息传递的方式相互学习，来建立决策树，同时将语意意义通过二进制属性的形式赋给每个决策，使其对用户更加精练、语义化和相关。在三个基准图像分类数据集上，包括大规模ImageNet数据集，该模型生成了人类可解释的二进制决策序列，解释了网络的预测情况，同时保持了最先进的准确性。

通过通信循环学习决策树