Interpretable Machine Learning

Bradley C. Boehmke, Brandon M. Greenwell
{"title":"Interpretable Machine Learning","authors":"Bradley C. Boehmke, Brandon M. Greenwell","doi":"10.1201/9780367816377-16","DOIUrl":null,"url":null,"abstract":"Interpretable machine learning has become a popular research direction as deep neural networks (DNNs) have become more powerful and their applications more mainstream, yet DNNs remain difficult to understand. Testing with Concept Activation Vectors, TCAV, (Kim et al. 2017) is an approach to interpreting DNNs in a human-friendly way and has recently received significant attention in the machine learning community. The TCAV algorithm achieves a degree of global interpretability for DNNs through human-defined concepts as explanations. This project introduces Robust TCAV, which builds on TCAV and experimentally determines best practices for this method. The objectives for Robust TCAV are 1) Making TCAV more consistent by reducing variance in the TCAV score distribution and 2) Increasing CAV and TCAV score resistance to perturbations. A difference of means method for CAV generation was determined to be the best practice to achieve both objectives. Many areas of the TCAV process are explored including CAV visualization in low dimensions, negative class selection, and activation perturbation in the direction of a CAV. Finally, a thresholding technique is considered to remove noise in TCAV scores. This project is a step in the direction of making TCAV, an already impactful algorithm in interpretability, more reliable and useful for practitioners.","PeriodicalId":369932,"journal":{"name":"Hands-On Machine Learning with R","volume":"10 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1888","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Hands-On Machine Learning with R","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1201/9780367816377-16","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1888

Abstract

Interpretable machine learning has become a popular research direction as deep neural networks (DNNs) have become more powerful and their applications more mainstream, yet DNNs remain difficult to understand. Testing with Concept Activation Vectors, TCAV, (Kim et al. 2017) is an approach to interpreting DNNs in a human-friendly way and has recently received significant attention in the machine learning community. The TCAV algorithm achieves a degree of global interpretability for DNNs through human-defined concepts as explanations. This project introduces Robust TCAV, which builds on TCAV and experimentally determines best practices for this method. The objectives for Robust TCAV are 1) Making TCAV more consistent by reducing variance in the TCAV score distribution and 2) Increasing CAV and TCAV score resistance to perturbations. A difference of means method for CAV generation was determined to be the best practice to achieve both objectives. Many areas of the TCAV process are explored including CAV visualization in low dimensions, negative class selection, and activation perturbation in the direction of a CAV. Finally, a thresholding technique is considered to remove noise in TCAV scores. This project is a step in the direction of making TCAV, an already impactful algorithm in interpretability, more reliable and useful for practitioners.
可解释机器学习
随着深度神经网络(deep neural networks, dnn)的强大和应用的主流化,可解释性机器学习已经成为一个流行的研究方向,但dnn仍然难以理解。使用概念激活向量(TCAV)进行测试(Kim et al. 2017)是一种以人类友好的方式解释dnn的方法,最近在机器学习社区受到了极大的关注。TCAV算法通过人类定义的概念作为解释,实现了dnn的一定程度的全局可解释性。本项目介绍了鲁棒TCAV,它建立在TCAV的基础上,并通过实验确定了该方法的最佳实践。稳健TCAV的目标是:1)通过减少TCAV评分分布的方差使TCAV更加一致;2)增加CAV和TCAV评分对扰动的抵抗力。确定了CAV生成的均数差法是实现这两个目标的最佳实践。TCAV过程的许多领域都进行了探索,包括低维CAV可视化、负类选择和CAV方向上的激活扰动。最后,采用阈值法去除TCAV分数中的噪声。TCAV是一个在可解释性方面已经很有影响力的算法,这个项目是朝着使TCAV对从业者更可靠和有用的方向迈出的一步。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书