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}
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.