arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.03632cs.LGcs.AIcs.CVstat.ML
收藏

从可解释的模型中进行可视化和知识发现

Visualisation and knowledge discovery from interpretable models

Bernoulli Institute, University of Groningen(格罗宁根大学伯努利研究所);School of Computer Science, University of Birmingham(伯明翰大学计算机学院)

Sreejita Ghosh, Peter Tino, Kerstin Bunte

摘要:

越来越多影响人类生活的部门正在使用机器学习(ML)工具。因此,了解其工作机制并评估其决策公平性的需求变得至关重要,从而迎来了可解释AI(XAI)时代。在这篇文章中,我们介绍了一些本质上可解释的模型,除了从数据集中提取知识和关于问题之外,这些模型还能够处理缺失值。这些模型还能够可视化分类器和决策边界:它们是学习矢量量化的基于角度的变体。我们已经在一个合成数据集和一个真实世界的数据集(来自UCI存储库的心脏病数据集)上演示了该算法。新开发的分类器有助于研究UCI数据集作为多类问题的复杂性。开发的分类器的性能与文献中报道的数据集,具有额外的可解释性的值,当数据集被视为一个二进制类的问题。

英文摘要:

Increasing number of sectors which affect human lives, are using Machine Learning (ML) tools. Hence the need for understanding their working mechanism and evaluating their fairness in decision-making, are becoming paramount, ushering in the era of Explainable AI (XAI). In this contribution we introduced a few intrinsically interpretable models which are also capable of dealing with missing values, in addition to extracting knowledge from the dataset and about the problem. These models are also capable of visualisation of the classifier and decision boundaries: they are the angle based variants of Learning Vector Quantization. We have demonstrated the algorithms on a synthetic dataset and a real-world one (heart disease dataset from the UCI repository). The newly developed classifiers helped in investigating the complexities of the UCI dataset as a multiclass problem. The performance of the developed classifiers were comparable to those reported in literature for this dataset, with additional value of interpretability, when the dataset was treated as a binary class problem.

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。

↑