基于AlexNet的树木和草地识别的实现

Wang Yun-Zhou, Zhu Min-Ling, Chen Lei, Zhao Peng, Liu Hao-Nan, Xu Bo-Lang
{"title":"基于AlexNet的树木和草地识别的实现","authors":"Wang Yun-Zhou, Zhu Min-Ling, Chen Lei, Zhao Peng, Liu Hao-Nan, Xu Bo-Lang","doi":"10.1109/ccis57298.2022.10016438","DOIUrl":null,"url":null,"abstract":"With the development of artificial intelligence technology, China is playing an increasingly important role in the field of object neural network recognition. In the past, people's understanding of neural network recognition was limited to the template matching model, which was simple and clear, but the model emphasized that the image must be completely consistent with the template in the brain to be recognized. However, AI recognition should not only recognize images consistent with the template, but also recognize images inconsistent with the template. The accuracy of the final training results reached 99.15%, exceeding the existing expectations. And AlexNet was born in 2012. On the model, AlexNet contains several relatively new technical points, and has successfully applied ReLU, Dropout, LRN and other Tricks in CNN for the first time. At the same time, AlexNet also uses the GPU for computing acceleration.","PeriodicalId":374660,"journal":{"name":"2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS)","volume":"130 6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Realization of tree and grass recognition based on AlexNet\",\"authors\":\"Wang Yun-Zhou, Zhu Min-Ling, Chen Lei, Zhao Peng, Liu Hao-Nan, Xu Bo-Lang\",\"doi\":\"10.1109/ccis57298.2022.10016438\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"With the development of artificial intelligence technology, China is playing an increasingly important role in the field of object neural network recognition. In the past, people's understanding of neural network recognition was limited to the template matching model, which was simple and clear, but the model emphasized that the image must be completely consistent with the template in the brain to be recognized. However, AI recognition should not only recognize images consistent with the template, but also recognize images inconsistent with the template. The accuracy of the final training results reached 99.15%, exceeding the existing expectations. And AlexNet was born in 2012. On the model, AlexNet contains several relatively new technical points, and has successfully applied ReLU, Dropout, LRN and other Tricks in CNN for the first time. At the same time, AlexNet also uses the GPU for computing acceleration.\",\"PeriodicalId\":374660,\"journal\":{\"name\":\"2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS)\",\"volume\":\"130 6 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ccis57298.2022.10016438\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ccis57298.2022.10016438","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

随着人工智能技术的发展,中国在目标神经网络识别领域发挥着越来越重要的作用。过去人们对神经网络识别的理解仅限于模板匹配模型,简单明了,但该模型强调图像必须与大脑中的模板完全一致才能被识别。但是,AI识别既要识别与模板一致的图像,也要识别与模板不一致的图像。最终的训练结果准确率达到99.15%,超过了现有的预期。AlexNet于2012年诞生。在模型上,AlexNet包含了几个相对较新的技术点,并首次在CNN中成功应用了ReLU、Dropout、LRN等Tricks。同时,AlexNet还使用GPU进行计算加速。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Realization of tree and grass recognition based on AlexNet
With the development of artificial intelligence technology, China is playing an increasingly important role in the field of object neural network recognition. In the past, people's understanding of neural network recognition was limited to the template matching model, which was simple and clear, but the model emphasized that the image must be completely consistent with the template in the brain to be recognized. However, AI recognition should not only recognize images consistent with the template, but also recognize images inconsistent with the template. The accuracy of the final training results reached 99.15%, exceeding the existing expectations. And AlexNet was born in 2012. On the model, AlexNet contains several relatively new technical points, and has successfully applied ReLU, Dropout, LRN and other Tricks in CNN for the first time. At the same time, AlexNet also uses the GPU for computing acceleration.
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
×
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:481959085
Book学术官方微信