サンプリングをずらすことによる機械学習の訓練データ水増し手法の検証

書誌事項

タイトル別名
  • An Investigation of Machine Learning Training Data Padding Method by Shifting Sampling

説明

<p>A large amount of data is necessary to obtain desired results in machine learning in which a robot substitutes humans’ manual labors. In addition, it is an explicit problem that it takes a lot of time and operating costs for it. In this research, we focus on down-sampling and decimation used in system identification and propose a method to reduce teacher data by padding data in machine learning.</p>

収録刊行物

詳細情報 詳細情報について

問題の指摘

ページトップへ