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  [in Japanese] An Investigation of Machine Learning Training Data Padding Method by Shifting Sampling  [in Japanese]

Access this Article

Author(s)

Abstract

<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>

Journal

  • The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)

    The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) 2019(0), 2A2-C03, 2019

    The Japan Society of Mechanical Engineers

Codes

Page Top