基于神经网络的支持神经形态架构的GUI流编辑器开发

Hoinam Kim, K. Kim, Chansoo Kim, Jinmang Jung, Young-Sun Yun
{"title":"基于神经网络的支持神经形态架构的GUI流编辑器开发","authors":"Hoinam Kim, K. Kim, Chansoo Kim, Jinmang Jung, Young-Sun Yun","doi":"10.1109/icghit49656.2020.00016","DOIUrl":null,"url":null,"abstract":"As the deep learning model develops, there is a technology called neuromorphic that increases the power consumption efficiency by constructing a circuit similar to a real human neuron. In the existing studies, users can easily create programs using prebuilt components, but many development tools do not support neuromorphic computing models for AI development. Therefore, in this paper, we want to create a development tool that supports the neuromorphic architecture based AI model, and implement the function that the user can directly create a component and add it to the development tool. Through this, we implemented a classifier using spiking neural network (SNN), one of the neuromorphic network models. The classifier evaluated a performance using the well known MNIST model and confirmed that the presented model works as expected.","PeriodicalId":377112,"journal":{"name":"2020 International Conference on Green and Human Information Technology (ICGHIT)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Development of GUI Flow Editor Supporting Neuromorphic Architecture Based Neural Network\",\"authors\":\"Hoinam Kim, K. Kim, Chansoo Kim, Jinmang Jung, Young-Sun Yun\",\"doi\":\"10.1109/icghit49656.2020.00016\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"As the deep learning model develops, there is a technology called neuromorphic that increases the power consumption efficiency by constructing a circuit similar to a real human neuron. In the existing studies, users can easily create programs using prebuilt components, but many development tools do not support neuromorphic computing models for AI development. Therefore, in this paper, we want to create a development tool that supports the neuromorphic architecture based AI model, and implement the function that the user can directly create a component and add it to the development tool. Through this, we implemented a classifier using spiking neural network (SNN), one of the neuromorphic network models. The classifier evaluated a performance using the well known MNIST model and confirmed that the presented model works as expected.\",\"PeriodicalId\":377112,\"journal\":{\"name\":\"2020 International Conference on Green and Human Information Technology (ICGHIT)\",\"volume\":\"8 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-02-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 International Conference on Green and Human Information Technology (ICGHIT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/icghit49656.2020.00016\",\"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 International Conference on Green and Human Information Technology (ICGHIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/icghit49656.2020.00016","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

随着深度学习模型的发展,有一种叫做神经形态的技术,通过构建类似于真实人类神经元的电路来提高功耗效率。在现有的研究中,用户可以使用预构建的组件轻松创建程序,但许多开发工具不支持用于人工智能开发的神经形态计算模型。因此,在本文中,我们希望创建一个支持基于神经形态架构的AI模型的开发工具,并实现用户可以直接创建组件并将其添加到开发工具中的功能。通过这种方法,我们使用神经形态网络模型之一的尖峰神经网络(SNN)实现了一个分类器。分类器使用众所周知的MNIST模型评估性能,并确认所提出的模型按预期工作。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Development of GUI Flow Editor Supporting Neuromorphic Architecture Based Neural Network
As the deep learning model develops, there is a technology called neuromorphic that increases the power consumption efficiency by constructing a circuit similar to a real human neuron. In the existing studies, users can easily create programs using prebuilt components, but many development tools do not support neuromorphic computing models for AI development. Therefore, in this paper, we want to create a development tool that supports the neuromorphic architecture based AI model, and implement the function that the user can directly create a component and add it to the development tool. Through this, we implemented a classifier using spiking neural network (SNN), one of the neuromorphic network models. The classifier evaluated a performance using the well known MNIST model and confirmed that the presented model works as expected.
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:604180095
Book学术官方微信