论文标题
在象征性编码随机森林的行为上
On Symbolically Encoding the Behavior of Random Forests
论文作者
论文摘要
最近的工作表明，某些机器学习系统的投入输出行为可以使用布尔表达式或可拖动的布尔电路象征性地捕获，这有助于对这些系统的行为进行推理。尽管大多数重点都放在具有布尔输入和输出的系统上，但我们解决了具有离散输入和输出的系统，包括基于决策树的系统中的离散连续变量的系统。我们还专注于对计算主要隐含物的编码的适用性，这些人最近在解释机器学习系统的决策方面发挥了核心作用。我们通过可满足的编码显示了一些关键的区别，并提出了针对给定任务的声音和完整的编码。
Recent work has shown that the input-output behavior of some machine learning systems can be captured symbolically using Boolean expressions or tractable Boolean circuits, which facilitates reasoning about the behavior of these systems. While most of the focus has been on systems with Boolean inputs and outputs, we address systems with discrete inputs and outputs, including ones with discretized continuous variables as in systems based on decision trees. We also focus on the suitability of encodings for computing prime implicants, which have recently played a central role in explaining the decisions of machine learning systems. We show some key distinctions with encodings for satisfiability, and propose an encoding that is sound and complete for the given task.
