XOC: Explainable Observer-Classifier for Explainable Binary Decisions.
arXiv: Learning(2019)
摘要
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 useru0027s trust towards the machine as they help develop a better understanding of the rationale behind the networku0027s predictions. Here, we present an explainable observer-classifier framework that exposes the steps taken through the modelu0027s 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 networku0027s predictions.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要