为什么要在机器学习中引入可解释性？一种基于分布式检测和数据融合理论的解决方案
Why Interpretability in Machine Learning? An Answer Using Distributed Detection and Data Fusion Theory
摘要：
随着人工智能越来越多地影响社会和生活的各个方面，人们越来越认识到人类对机器学习模型的可解释性非常重要。通常认为，为了获得可解释性，必须牺牲准确性或其他类似的泛化性能指标。然而，这些论点没有承认整个决策系统由两个实体组成：学习模型和将模型输出与他或她自己的信息融合在一起的人。因此，相关的性能标准应该针对整个系统，而不仅仅是机器学习组件。在这项工作中，我们的特点，这样的两个节点的串联数据融合系统的分布式检测理论的性能。在这样做的过程中，我们在人口设置和模型可解释的学习模型作为多级量化器。我们证明，在我们的抽象，一个人的整体系统与可解释的分类器优于一个黑盒分类器。
英文摘要：
As artificial intelligence is increasingly affecting all parts of society and life, there is growing recognition that human interpretability of machine learning models is important. It is often argued that accuracy or other similar generalization performance metrics must be sacrificed in order to gain interpretability. Such arguments, however, fail to acknowledge that the overall decision-making system is composed of two entities: the learned model and a human who fuses together model outputs with his or her own information. As such, the relevant performance criteria should be for the entire system, not just for the machine learning component. In this work, we characterize the performance of such two-node tandem data fusion systems using the theory of distributed detection. In doing so, we work in the population setting and model interpretable learned models as multi-level quantizers. We prove that under our abstraction, the overall system of a human with an interpretable classifier outperforms one with a black box classifier.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
