进化生成贡献映射

Masayuki Kobayashi, Satoshi Arai, T. Nagao
{"title":"进化生成贡献映射","authors":"Masayuki Kobayashi, Satoshi Arai, T. Nagao","doi":"10.1109/SMC42975.2020.9283014","DOIUrl":null,"url":null,"abstract":"Although convolutional neural networks (CNNs) have significantly evolved and demonstrated outstanding performance, their uninterpretable nature is still considered to be a major problem. In this study, we take a closer look at CNN interpretability and propose a new method called Evolutionary Generative Contribution Mappings (EGCM). In EGCM, CNN models incorporate both a classification mechanism and an interpreting mechanism in an end-to-end training process. Specifically, the network generates the class contribution maps, which indicate the discriminative regions for the model to identify a specific class. Additionally, these maps can be directly used for classification tasks; all that is needed is a global average pooling and a softmax function. The network is represented by a directed acyclic graph and optimized using a genetic algorithm. Architecture search enables EGCM to deliver reasonable classification performance while maintaining high interpretability. We apply the EGCM framework on several datasets and empirically demonstrate that the EGCM not only achieves excellent classification performance but also maintains high interpretability.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"34 1","pages":"1657-1664"},"PeriodicalIF":0.0000,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Evolutionary Generative Contribution Mappings\",\"authors\":\"Masayuki Kobayashi, Satoshi Arai, T. Nagao\",\"doi\":\"10.1109/SMC42975.2020.9283014\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Although convolutional neural networks (CNNs) have significantly evolved and demonstrated outstanding performance, their uninterpretable nature is still considered to be a major problem. In this study, we take a closer look at CNN interpretability and propose a new method called Evolutionary Generative Contribution Mappings (EGCM). In EGCM, CNN models incorporate both a classification mechanism and an interpreting mechanism in an end-to-end training process. Specifically, the network generates the class contribution maps, which indicate the discriminative regions for the model to identify a specific class. Additionally, these maps can be directly used for classification tasks; all that is needed is a global average pooling and a softmax function. The network is represented by a directed acyclic graph and optimized using a genetic algorithm. Architecture search enables EGCM to deliver reasonable classification performance while maintaining high interpretability. We apply the EGCM framework on several datasets and empirically demonstrate that the EGCM not only achieves excellent classification performance but also maintains high interpretability.\",\"PeriodicalId\":6718,\"journal\":{\"name\":\"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)\",\"volume\":\"34 1\",\"pages\":\"1657-1664\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-10-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SMC42975.2020.9283014\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SMC42975.2020.9283014","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

虽然卷积神经网络(cnn)已经有了显著的发展,并表现出出色的性能,但其不可解释的性质仍然被认为是一个主要问题。在这项研究中,我们仔细研究了CNN的可解释性,并提出了一种名为进化生成贡献映射(EGCM)的新方法。在EGCM中,CNN模型在端到端训练过程中结合了分类机制和解释机制。具体来说,网络生成类贡献图,它指示模型识别特定类的判别区域。此外,这些地图可以直接用于分类任务;所需要的只是一个全局平均池和一个softmax函数。该网络用有向无环图表示,并采用遗传算法进行优化。架构搜索使EGCM能够在保持高可解释性的同时提供合理的分类性能。我们将EGCM框架应用于多个数据集上,实证表明EGCM不仅取得了优异的分类性能,而且保持了较高的可解释性。
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
Evolutionary Generative Contribution Mappings
Although convolutional neural networks (CNNs) have significantly evolved and demonstrated outstanding performance, their uninterpretable nature is still considered to be a major problem. In this study, we take a closer look at CNN interpretability and propose a new method called Evolutionary Generative Contribution Mappings (EGCM). In EGCM, CNN models incorporate both a classification mechanism and an interpreting mechanism in an end-to-end training process. Specifically, the network generates the class contribution maps, which indicate the discriminative regions for the model to identify a specific class. Additionally, these maps can be directly used for classification tasks; all that is needed is a global average pooling and a softmax function. The network is represented by a directed acyclic graph and optimized using a genetic algorithm. Architecture search enables EGCM to deliver reasonable classification performance while maintaining high interpretability. We apply the EGCM framework on several datasets and empirically demonstrate that the EGCM not only achieves excellent classification performance but also maintains high interpretability.
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
自引率
0.00%
发文量
0
期刊最新文献
At-the-Edge Data Processing for Low Latency High Throughput Machine Learning Algorithms Machine Learning for First Principles Calculations of Material Properties for Ferromagnetic Materials Mobility Aware Computation Offloading Model for Edge Computing Toward an Autonomous Workflow for Single Crystal Neutron Diffraction Virtual Infrastructure Twins: Software Testing Platforms for Computing-Instrument Ecosystems
×
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