混合深度学习gmdh -neo-模糊神经网络及其应用

2019 IEEE 13th International Conference on Application of Information and Communication Technologies (AICT) Pub Date : 2019-10-01 DOI:10.1109/AICT47866.2019.8981725

Y. Zaychenko, Galib Hamidov

{"title":"混合深度学习gmdh -neo-模糊神经网络及其应用","authors":"Y. Zaychenko, Galib Hamidov","doi":"10.1109/AICT47866.2019.8981725","DOIUrl":null,"url":null,"abstract":"The hybrid deep learning GMDH- neo-fuzzy network was suggested and investigated. The application of GMDH based on self-organization enables to build optimal structure of neo-fuzzy system and train weights of neural network in one procedure. As a node of hybrid neo-fuzzy system neo-fuzzy network with small number of adjustable parameters is suggested. This enables to cut training time and accelerate convergence of training. The experimental studies of GMDH-neo-fuzzy network were carried out in the task of forecasting in macro-economy and financial sphere. The forecasting efficiency of the suggested hybrid neo-fuzzy network was estimated and its sensitivity to variation of tuning parameters was investigated. The suggested approach allows to prevent the drawbacks of deep learning such as vanishing or exploding gradient.","PeriodicalId":329473,"journal":{"name":"2019 IEEE 13th International Conference on Application of Information and Communication Technologies (AICT)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"The Hybrid Deep Learning GMDH-neo-fuzzy Neural Network and Its Applications\",\"authors\":\"Y. Zaychenko, Galib Hamidov\",\"doi\":\"10.1109/AICT47866.2019.8981725\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The hybrid deep learning GMDH- neo-fuzzy network was suggested and investigated. The application of GMDH based on self-organization enables to build optimal structure of neo-fuzzy system and train weights of neural network in one procedure. As a node of hybrid neo-fuzzy system neo-fuzzy network with small number of adjustable parameters is suggested. This enables to cut training time and accelerate convergence of training. The experimental studies of GMDH-neo-fuzzy network were carried out in the task of forecasting in macro-economy and financial sphere. The forecasting efficiency of the suggested hybrid neo-fuzzy network was estimated and its sensitivity to variation of tuning parameters was investigated. The suggested approach allows to prevent the drawbacks of deep learning such as vanishing or exploding gradient.\",\"PeriodicalId\":329473,\"journal\":{\"name\":\"2019 IEEE 13th International Conference on Application of Information and Communication Technologies (AICT)\",\"volume\":\"35 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 IEEE 13th International Conference on Application of Information and Communication Technologies (AICT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/AICT47866.2019.8981725\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE 13th International Conference on Application of Information and Communication Technologies (AICT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AICT47866.2019.8981725","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 3

摘要

提出并研究了混合深度学习GMDH- neo-fuzzy网络。基于自组织的GMDH的应用可以在一个过程中建立新模糊系统的最优结构和训练神经网络的权值。作为混合新模糊系统的一个节点，提出了具有少量可调参数的新模糊网络。这样可以缩短培训时间，加快培训的收敛速度。在宏观经济和金融领域的预测任务中，对gmdh -新模糊网络进行了实验研究。估计了所提出的混合新模糊网络的预测效率，并研究了其对整定参数变化的敏感性。建议的方法可以防止深度学习的缺点，例如梯度消失或爆炸。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

The Hybrid Deep Learning GMDH-neo-fuzzy Neural Network and Its Applications

The hybrid deep learning GMDH- neo-fuzzy network was suggested and investigated. The application of GMDH based on self-organization enables to build optimal structure of neo-fuzzy system and train weights of neural network in one procedure. As a node of hybrid neo-fuzzy system neo-fuzzy network with small number of adjustable parameters is suggested. This enables to cut training time and accelerate convergence of training. The experimental studies of GMDH-neo-fuzzy network were carried out in the task of forecasting in macro-economy and financial sphere. The forecasting efficiency of the suggested hybrid neo-fuzzy network was estimated and its sensitivity to variation of tuning parameters was investigated. The suggested approach allows to prevent the drawbacks of deep learning such as vanishing or exploding gradient.

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

2019 IEEE 13th International Conference on Application of Information and Communication Technologies (AICT)

自引率

0.00%

发文量