DOI QR코드

DOI QR Code

데이터 예측 모델 최적화를 위한 경사하강법 교육 방법

Gradient Descent Training Method for Optimizing Data Prediction Models

  • 허경 (경인교육대학교 컴퓨터교육과)
  • Hur, Kyeong (Department of Computer Education, Gyeong-In National University of Education)
  • 투고 : 2022.07.31
  • 심사 : 2022.08.19
  • 발행 : 2022.08.31

초록

본 논문에서는 기초적인 데이터 예측 모델을 만들고 최적화하는 교육에 초점을 맞추었다. 그리고 데이터 예측 모델을 최적화하는 데 널리 사용되는 머신러닝의 경사하강법 교육 방법을 제안하였다. 미분법을 적용하여 데이터 예측 모델에 필요한 파라미터 값들을 최적화하는 과정에 사용되는 경사하강법의 전체 동작과정을 시각적으로 보여주며, 수학의 미분법이 머신러닝에 효과적으로 사용되는 것을 교육한다. 경사하강법의 전체 동작과정을 시각적으로 설명하기위해, 스프레드시트로 경사하강법 SW를 구현한다. 본 논문에서는 첫번째로, 2변수 경사하강법 교육 방법을 제시하고, 오차 최소제곱법과 비교하여 2변수 데이터 예측모델의 정확도를 검증한다. 두번째로, 3변수 경사하강법 교육 방법을 제시하고, 3변수 데이터 예측모델의 정확도를 검증한다. 이후, 경사하강법 최적화 실습 방향을 제시하고, 비전공자 교육 만족도 결과를 통해, 제안한 경사하강법 교육방법이 갖는 교육 효과를 분석하였다.

In this paper, we focused on training to create and optimize a basic data prediction model. And we proposed a gradient descent training method of machine learning that is widely used to optimize data prediction models. It visually shows the entire operation process of gradient descent used in the process of optimizing parameter values required for data prediction models by applying the differential method and teaches the effective use of mathematical differentiation in machine learning. In order to visually explain the entire operation process of gradient descent, we implement gradient descent SW in a spreadsheet. In this paper, first, a two-variable gradient descent training method is presented, and the accuracy of the two-variable data prediction model is verified by comparison with the error least squares method. Second, a three-variable gradient descent training method is presented and the accuracy of a three-variable data prediction model is verified. Afterwards, the direction of the optimization practice for gradient descent was presented, and the educational effect of the proposed gradient descent method was analyzed through the results of satisfaction with education for non-majors.

키워드

참고문헌

  1. Ministry of Science and ICT, The 4th Industrial Revolution in History, R & D KIOSK, No. 40, September 2017.
  2. Ministry of Science and ICT, The Various Aspects of the Fourth Industrial Revolution, The Realized Future, R & D KIOSK, no. 41, October 2017.
  3. J. Y. Kim, Hello Data Science, Seoul : Hanbit Media, 2016.
  4. J. K. Kwon, Learning Data Science, Seoul : Jpub, 2020.
  5. U. Ichiro, N. Hiroaki, A. Masami, and M. Eichi, Learning Data science with Excel, Seoul : Hanbit Media, 2020.
  6. Ministry of Science and ICT, Beyond an IT Powerhouse to an AI Powerhouse, Report Material, 2019.
  7. Joint Ministries, Artificial Intelligence National Strategy, Report Material, 2019.
  8. Y. J. Jang, "Searching for the direction of data science education in the era of the 4th industrial revolution," Integrated Humanities Research, vol. 9, no.10, pp. 155-180, 2017.
  9. Y. S. Park and S. J. Lee, "Study on the direction of universal big data and big data education-based on the survey of big data experts," Journal of the Korean Association of Information Education, vol. 24, no. 2, pp. 201-214, 2020. https://doi.org/10.14352/jkaie.2020.24.2.201
  10. Y. M. Kim and J. H. Kim, "Effect of data science education program using spreadsheet on improvement of elementary school computational thinking," Journal of the Korean Association of Information Education, vol. 21, no. 2, pp. 219-230. 2017. https://doi.org/10.14352/jkaie.21.2.219
  11. J. S. Lee, "A study on visualization methods and expressions of information design for big data, basic formulation studies," Korean Society of Basic Design & Art, vol. 14, no. 3, pp. 261-269, 2013.
  12. K. Hur, "Curriculum of basic data science practices for non-majors," Journal of Practical Engineering Education, vol. 12, no. 2, pp. 265-273, 2020. https://doi.org/10.14702/JPEE.2020.265
  13. W. Yoshiyuki and W. Sadami, Machine Learning with Excel, Seoul : Seongandang, 2021.