基于形式概念分析分类器的可解释图像分类模型

Minal Khatri, Adam Voshall, S. Batra, Sukhwinder Kaur, Dr. Jitender S. Deogun
{"title":"基于形式概念分析分类器的可解释图像分类模型","authors":"Minal Khatri, Adam Voshall, S. Batra, Sukhwinder Kaur, Dr. Jitender S. Deogun","doi":"10.29007/rp6q","DOIUrl":null,"url":null,"abstract":"Massive amounts of data gathered over the last decade have contributed significantly to the applicability of deep neural networks. Deep learning is a good technique to process huge amounts of data because they get better as we feed more data into them. However, in the existing literature, a deep neural classifier is often treated as a ”black box” technique because the process is not transparent and the researchers cannot gain information about how the input is associated to the output. In many domains like medicine, interpretability is very critical because of the nature of the application. Our research focuses on adding interpretability to the black box by integrating Formal Concept Analysis (FCA) into the image classification pipeline and convert it into a glass box. Our proposed approach pro- duces a low dimensional feature vector for an image dataset using autoencoder followed by a supervised fine-tuning of features using a deep neural classifier and Linear Discriminant Analysis (LDA). The low dimensional feature vector produced is then processed by FCA based classifier. The FCA framework helps us develop a glass box classifier from which the relationship between the target class and the low dimensional feature set can be derived. Further, it helps the researchers to understand the classification task and refine it. We use the MNIST dataset to test the interfacing between deep neural networks and the FCA classifier. The classifier achieves an accuracy of 98.7% for binary classification and 97.38% for multi-class classification. We compare the performance of the proposed classifier with Convolutional neural networks (CNN) and Random forest.","PeriodicalId":93549,"journal":{"name":"EPiC series in computing","volume":"1 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Interpretable Image Classification Model Using Formal Concept Analysis Based Classifier\",\"authors\":\"Minal Khatri, Adam Voshall, S. Batra, Sukhwinder Kaur, Dr. Jitender S. Deogun\",\"doi\":\"10.29007/rp6q\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Massive amounts of data gathered over the last decade have contributed significantly to the applicability of deep neural networks. Deep learning is a good technique to process huge amounts of data because they get better as we feed more data into them. However, in the existing literature, a deep neural classifier is often treated as a ”black box” technique because the process is not transparent and the researchers cannot gain information about how the input is associated to the output. In many domains like medicine, interpretability is very critical because of the nature of the application. Our research focuses on adding interpretability to the black box by integrating Formal Concept Analysis (FCA) into the image classification pipeline and convert it into a glass box. Our proposed approach pro- duces a low dimensional feature vector for an image dataset using autoencoder followed by a supervised fine-tuning of features using a deep neural classifier and Linear Discriminant Analysis (LDA). The low dimensional feature vector produced is then processed by FCA based classifier. The FCA framework helps us develop a glass box classifier from which the relationship between the target class and the low dimensional feature set can be derived. Further, it helps the researchers to understand the classification task and refine it. We use the MNIST dataset to test the interfacing between deep neural networks and the FCA classifier. The classifier achieves an accuracy of 98.7% for binary classification and 97.38% for multi-class classification. We compare the performance of the proposed classifier with Convolutional neural networks (CNN) and Random forest.\",\"PeriodicalId\":93549,\"journal\":{\"name\":\"EPiC series in computing\",\"volume\":\"1 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"EPiC series in computing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.29007/rp6q\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"EPiC series in computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.29007/rp6q","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

过去十年中收集的大量数据对深度神经网络的适用性做出了重大贡献。深度学习是一种处理大量数据的好技术,因为当我们输入更多数据时,它们会变得更好。然而,在现有文献中,深度神经分类器通常被视为“黑箱”技术,因为该过程不透明,研究人员无法获得有关输入与输出如何关联的信息。在许多领域,如医学,可解释性是非常关键的,因为应用程序的性质。我们的研究重点是通过将形式概念分析(FCA)集成到图像分类管道中,并将其转换为一个玻璃盒,从而增加黑箱的可解释性。我们提出的方法是使用自编码器为图像数据集生成低维特征向量,然后使用深度神经分类器和线性判别分析(LDA)对特征进行监督微调。生成的低维特征向量通过基于FCA的分类器进行处理。FCA框架帮助我们开发一个玻璃盒分类器,从中可以导出目标类和低维特征集之间的关系。此外,它有助于研究人员理解分类任务并对其进行改进。我们使用MNIST数据集来测试深度神经网络和FCA分类器之间的接口。该分类器对二分类的准确率为98.7%,对多分类的准确率为97.38%。我们将所提出的分类器与卷积神经网络(CNN)和随机森林的性能进行了比较。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Interpretable Image Classification Model Using Formal Concept Analysis Based Classifier
Massive amounts of data gathered over the last decade have contributed significantly to the applicability of deep neural networks. Deep learning is a good technique to process huge amounts of data because they get better as we feed more data into them. However, in the existing literature, a deep neural classifier is often treated as a ”black box” technique because the process is not transparent and the researchers cannot gain information about how the input is associated to the output. In many domains like medicine, interpretability is very critical because of the nature of the application. Our research focuses on adding interpretability to the black box by integrating Formal Concept Analysis (FCA) into the image classification pipeline and convert it into a glass box. Our proposed approach pro- duces a low dimensional feature vector for an image dataset using autoencoder followed by a supervised fine-tuning of features using a deep neural classifier and Linear Discriminant Analysis (LDA). The low dimensional feature vector produced is then processed by FCA based classifier. The FCA framework helps us develop a glass box classifier from which the relationship between the target class and the low dimensional feature set can be derived. Further, it helps the researchers to understand the classification task and refine it. We use the MNIST dataset to test the interfacing between deep neural networks and the FCA classifier. The classifier achieves an accuracy of 98.7% for binary classification and 97.38% for multi-class classification. We compare the performance of the proposed classifier with Convolutional neural networks (CNN) and Random forest.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
1.60
自引率
0.00%
发文量
0
期刊最新文献
ARCH-COMP23 Category Report: Hybrid Systems Theorem Proving ARCH-COMP23 Category Report: Continuous and Hybrid Systems with Linear Continuous Dynamics ARCH-COMP23 Category Report: Continuous and Hybrid Systems with Nonlinear Dynamics ARCH-COMP23 Repeatability Evaluation Report ARCH-COMP23 Category Report: Artificial Intelligence and Neural Network Control Systems (AINNCS) for Continuous and Hybrid Systems Plants
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1