卷积神经网络(CNN)的发展与应用综述

Sandeep Joshi, M. Manu, Amit Mittal
{"title":"卷积神经网络(CNN)的发展与应用综述","authors":"Sandeep Joshi, M. Manu, Amit Mittal","doi":"10.1109/ICECAA58104.2023.10212250","DOIUrl":null,"url":null,"abstract":"Within this literary document, a panoramic insight is presented on the progression and practical uses of Convolutional Neural Networks (CNNs), an influential technique in deep learning that serves as a major element within computer vision research alongside other areas. Through a comprehensive analysis of the literature, this research study presents thehistorical development of CNNs from early work on perceptrons to current state-of-the-art architectures like VGGNet, ResNet, and EfficientNet. The review highlights the key contributions of CNNs in various fields, such as image and video recognition, natural language processing, and audio analysis. Furthermore, it discusses the potential for further research and development of CNNs, including the challenges in training and optimizing CNNs and the future directions of CNNs. Overall, this review underscores the importance of CNNs in enabling breakthroughsin diverse fields and their potential for continued impact on the scientific community.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Review of the Evolution and Applications of Convolutional Neural Network (CNN)\",\"authors\":\"Sandeep Joshi, M. Manu, Amit Mittal\",\"doi\":\"10.1109/ICECAA58104.2023.10212250\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Within this literary document, a panoramic insight is presented on the progression and practical uses of Convolutional Neural Networks (CNNs), an influential technique in deep learning that serves as a major element within computer vision research alongside other areas. Through a comprehensive analysis of the literature, this research study presents thehistorical development of CNNs from early work on perceptrons to current state-of-the-art architectures like VGGNet, ResNet, and EfficientNet. The review highlights the key contributions of CNNs in various fields, such as image and video recognition, natural language processing, and audio analysis. Furthermore, it discusses the potential for further research and development of CNNs, including the challenges in training and optimizing CNNs and the future directions of CNNs. Overall, this review underscores the importance of CNNs in enabling breakthroughsin diverse fields and their potential for continued impact on the scientific community.\",\"PeriodicalId\":114624,\"journal\":{\"name\":\"2023 2nd International Conference on Edge Computing and Applications (ICECAA)\",\"volume\":\"29 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-07-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 2nd International Conference on Edge Computing and Applications (ICECAA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICECAA58104.2023.10212250\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICECAA58104.2023.10212250","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

在这篇文献中,对卷积神经网络(cnn)的进展和实际应用进行了全面的了解,卷积神经网络是深度学习中有影响力的技术,与其他领域一起作为计算机视觉研究的主要元素。通过对文献的全面分析,本研究展示了cnn的历史发展,从早期的感知器工作到当前最先进的架构,如VGGNet、ResNet和EfficientNet。这篇综述强调了cnn在各个领域的主要贡献,如图像和视频识别、自然语言处理和音频分析。此外,本文还讨论了cnn进一步研究和发展的潜力,包括训练和优化cnn所面临的挑战以及cnn的未来方向。总的来说,这篇综述强调了cnn在不同领域实现突破的重要性,以及它们对科学界持续影响的潜力。
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
A Review of the Evolution and Applications of Convolutional Neural Network (CNN)
Within this literary document, a panoramic insight is presented on the progression and practical uses of Convolutional Neural Networks (CNNs), an influential technique in deep learning that serves as a major element within computer vision research alongside other areas. Through a comprehensive analysis of the literature, this research study presents thehistorical development of CNNs from early work on perceptrons to current state-of-the-art architectures like VGGNet, ResNet, and EfficientNet. The review highlights the key contributions of CNNs in various fields, such as image and video recognition, natural language processing, and audio analysis. Furthermore, it discusses the potential for further research and development of CNNs, including the challenges in training and optimizing CNNs and the future directions of CNNs. Overall, this review underscores the importance of CNNs in enabling breakthroughsin diverse fields and their potential for continued impact on the scientific community.
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
Deep Learning based Sentiment Analysis on Images A Comprehensive Analysis on Unconstraint Video Analysis Using Deep Learning Approaches An Intelligent Parking Lot Management System Based on Real-Time License Plate Recognition BLIP-NLP Model for Sentiment Analysis Botnet Attack Detection in IoT Networks using CNN and LSTM
×
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