{"product_id":"ieej-st18076","title":"Prioritized Sampling Method for Autoencoder to Reduce Loss Rate for Skewed Data","description":"\u003cp\u003e\u003cstrong\u003eカテゴリ: \u003c\/strong\u003e研究会(論文単位)\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e論文No: \u003c\/strong\u003eST18076\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eグループ名: \u003c\/strong\u003e【C】電子・情報・システム部門 システム研究会\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e発行日: \u003c\/strong\u003e2018\/09\/26\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eタイトル(英語): \u003c\/strong\u003ePrioritized Sampling Method for Autoencoder to Reduce Loss Rate for Skewed Data\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e著者名: \u003c\/strong\u003e李 欣(横浜国立大学),濱上 知樹(横浜国立大学)\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e著者名(英語): \u003c\/strong\u003eXin Li(Yokohama National University),Tomoki Hamagami(Yokohama National University)\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eキーワード: \u003c\/strong\u003eAutoencoder|Skewed Data|Deep Learning|Prioritized|Sampling|Loss Rate\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e要約(日本語): \u003c\/strong\u003eWith the development of machine learning and deep learning in recent years, many topics in production and industry have used these technologies. However, in real life, there are a lot of data that is skewed, which means that the data is not so uniform, which results in the inability to obtain correct features when using machine learning to train, or to cause the error value is extremely high and not evenly distributed in this part of the data, for this reason we will lose the meaning of machine learning. Especially when using Autoencoder to do low dimensional compression or feature extraction, skewed data will lead to Autoencoder can not well compress the characteristics of this part of the offset data. In this research, we improved the general Denoising Autoencoder, used a iterated method to solve the problem bring from skewed data.\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e要約(英語): \u003c\/strong\u003eWith the development of machine learning and deep learning in recent years, many topics in production and industry have used these technologies. However, in real life, there are a lot of data that is skewed, which means that the data is not so uniform, which results in the inability to obtain correct features when using machine learning to train, or to cause the error value is extremely high and not evenly distributed in this part of the data, for this reason we will lose the meaning of machine learning. Especially when using Autoencoder to do low dimensional compression or feature extraction, skewed data will lead to Autoencoder can not well compress the characteristics of this part of the offset data. In this research, we improved the general Denoising Autoencoder, used a iterated method to solve the problem bring from skewed data.\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e原稿種別: \u003c\/strong\u003e英語\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003ePDFファイルサイズ: \u003c\/strong\u003e3,027 Kバイト\u003c\/p\u003e","brand":"IEEJ-PDF","offers":[{"title":"PDFダウンロード（一般価格330円\/会員価格220円） \/ A4 \/ 5","offer_id":46390748283119,"sku":"IEEJ-ST18076-PDF","price":330.0,"currency_code":"JPY","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0718\/9512\/2159\/files\/IEEJ-PDF_03821bc9-baa2-40fc-a8a8-3be729c36ec2.png?v=1744602445","url":"https:\/\/ieej.bookpark.ne.jp\/products\/ieej-st18076","provider":"電気学会 電子図書館","version":"1.0","type":"link"}