Browse > Article
http://dx.doi.org/10.14702/JPEE.2022.305

Gradient Descent Training Method for Optimizing Data Prediction Models  

Hur, Kyeong (Department of Computer Education, Gyeong-In National University of Education)
Publication Information
Journal of Practical Engineering Education / v.14, no.2, 2022 , pp. 305-312 More about this Journal
Abstract
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.
Keywords
Data prediction model; AI education; Machine learning; Non-major undergraduates; Gradient descent method;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 Ministry of Science and ICT, The 4th Industrial Revolution in History, R & D KIOSK, No. 40, September 2017.
2 J. Y. Kim, Hello Data Science, Seoul : Hanbit Media, 2016.
3 J. K. Kwon, Learning Data Science, Seoul : Jpub, 2020.
4 Ministry of Science and ICT, Beyond an IT Powerhouse to an AI Powerhouse, Report Material, 2019.
5 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.   DOI
6 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.   DOI
7 K. Hur, "Curriculum of basic data science practices for non-majors," Journal of Practical Engineering Education, vol. 12, no. 2, pp. 265-273, 2020.   DOI
8 W. Yoshiyuki and W. Sadami, Machine Learning with Excel, Seoul : Seongandang, 2021.
9 Joint Ministries, Artificial Intelligence National Strategy, Report Material, 2019.
10 Ministry of Science and ICT, The Various Aspects of the Fourth Industrial Revolution, The Realized Future, R & D KIOSK, no. 41, October 2017.
11 U. Ichiro, N. Hiroaki, A. Masami, and M. Eichi, Learning Data science with Excel, Seoul : Hanbit Media, 2020.
12 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.
13 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.