Hamideh Rezaei Nezhad, Farshid Keynia, Amir Sabagh Molahosseini
{"title":"优化深度网络结构以提高深度网络学习中估计器算法的准确性","authors":"Hamideh Rezaei Nezhad, Farshid Keynia, Amir Sabagh Molahosseini","doi":"10.24200/sci.2023.62337.7782","DOIUrl":null,"url":null,"abstract":"An optimization algorithm based on training and learning is formed based on the process of training and learning in a class. A deep neural network is one of the types of feedforward neural networks whose connection pattern among its neurons is inspired by the visual cortex of animals' brain. The present study considers decreasing prediction error for the types of time series and the uncertainty in estimation parameters, improving the structure of the deep neural network and increasing response speed in the proposed neural network method; besides, the competitive performance and the collaboration among the neurons of deep neural network are also increased. Selected data is related to Qeshm weather (suitable weather conditions to study our purpose) prediction during 2016 onwards. In this study, for the purpose of analyzing the prediction issue of power consumption of domestic expenses in the indefinite and severe fluctuation mode, we decided to combine two methods of Long Short-Term Memory and Convolutional Neural Network. For the training of the deep network, the BP algorithm is used.","PeriodicalId":21605,"journal":{"name":"Scientia Iranica","volume":null,"pages":null},"PeriodicalIF":1.4000,"publicationDate":"2023-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Optimized Deep Networks Structure to Improve the Accuracy of estimator algorithm in Deep Networks learning\",\"authors\":\"Hamideh Rezaei Nezhad, Farshid Keynia, Amir Sabagh Molahosseini\",\"doi\":\"10.24200/sci.2023.62337.7782\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"An optimization algorithm based on training and learning is formed based on the process of training and learning in a class. A deep neural network is one of the types of feedforward neural networks whose connection pattern among its neurons is inspired by the visual cortex of animals' brain. The present study considers decreasing prediction error for the types of time series and the uncertainty in estimation parameters, improving the structure of the deep neural network and increasing response speed in the proposed neural network method; besides, the competitive performance and the collaboration among the neurons of deep neural network are also increased. Selected data is related to Qeshm weather (suitable weather conditions to study our purpose) prediction during 2016 onwards. In this study, for the purpose of analyzing the prediction issue of power consumption of domestic expenses in the indefinite and severe fluctuation mode, we decided to combine two methods of Long Short-Term Memory and Convolutional Neural Network. For the training of the deep network, the BP algorithm is used.\",\"PeriodicalId\":21605,\"journal\":{\"name\":\"Scientia Iranica\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.4000,\"publicationDate\":\"2023-08-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Scientia Iranica\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.24200/sci.2023.62337.7782\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Scientia Iranica","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.24200/sci.2023.62337.7782","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}
Optimized Deep Networks Structure to Improve the Accuracy of estimator algorithm in Deep Networks learning
An optimization algorithm based on training and learning is formed based on the process of training and learning in a class. A deep neural network is one of the types of feedforward neural networks whose connection pattern among its neurons is inspired by the visual cortex of animals' brain. The present study considers decreasing prediction error for the types of time series and the uncertainty in estimation parameters, improving the structure of the deep neural network and increasing response speed in the proposed neural network method; besides, the competitive performance and the collaboration among the neurons of deep neural network are also increased. Selected data is related to Qeshm weather (suitable weather conditions to study our purpose) prediction during 2016 onwards. In this study, for the purpose of analyzing the prediction issue of power consumption of domestic expenses in the indefinite and severe fluctuation mode, we decided to combine two methods of Long Short-Term Memory and Convolutional Neural Network. For the training of the deep network, the BP algorithm is used.
期刊介绍:
The objectives of Scientia Iranica are two-fold. The first is to provide a forum for the presentation of original works by scientists and engineers from around the world. The second is to open an effective channel to enhance the level of communication between scientists and engineers and the exchange of state-of-the-art research and ideas.
The scope of the journal is broad and multidisciplinary in technical sciences and engineering. It encompasses theoretical and experimental research. Specific areas include but not limited to chemistry, chemical engineering, civil engineering, control and computer engineering, electrical engineering, material, manufacturing and industrial management, mathematics, mechanical engineering, nuclear engineering, petroleum engineering, physics, nanotechnology.