4.7 Article

PIP: Pictorial Interpretable Prototype Learning for Time Series Classification

期刊

IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE
卷 17, 期 1, 页码 34-45

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/MCI.2021.3129957

关键词

-

资金

  1. National Institutes of Health [R01NR016732, R01EB009675]

向作者/读者索取更多资源

The PIP architecture is designed to provide tailored explanations for specific end users in time series classification. By allowing users to train the model on their choice of class illustrations, PIP can create user-friendly explanations and offer an improved combination of accuracy and interpretability.
Time series classifiers are not only challenging to design, but they are also notoriously difficult to deploy for critical applications because end users may not understand or trust black-box models. Despite new efforts, explanations generated by other interpretable time series models are complicated for non-engineers to understand. The goal of PIP is to provide time series explanations that are tailored toward specific end users. To address the challenge, this paper introduces PIP, a novel deep learning architecture that jointly learns classification models and meaningful visual class prototypes. PIP allows users to train the model on their choice of class illustrations. Thus, PIP can create a user-friendly explanation by leaning on end-users definitions. We hypothesize that a pictorial description is an effective way to communicate a learned concept to non-expert users. Based on an end-user experiment with participants from multiple backgrounds, PIP offers an improved combination of accuracy and interpretability over baseline methods for time series classification.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据