• Title/Summary/Keyword: SW 비전공자

Search Result 42, Processing Time 0.017 seconds

Gradient Descent Training Method for Optimizing Data Prediction Models (데이터 예측 모델 최적화를 위한 경사하강법 교육 방법)

  • Hur, Kyeong
    • Journal of Practical Engineering Education
    • /
    • v.14 no.2
    • /
    • pp.305-312
    • /
    • 2022
  • 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.

Effects of Programming Education using Visual Literacy: Focus on Arts Major (시각적 문해력을 활용한 프로그래밍 교육의 효과 : 예술계열 중심으로)

  • Su-Young Pi;Hyun-Sook Son
    • Journal of Practical Engineering Education
    • /
    • v.16 no.2
    • /
    • pp.105-114
    • /
    • 2024
  • Recently, with an emphasis on software proficiency, universities are providing software education to all students regardless of their majors. However, non-majors often lack motivation for software education and perceive the unfamiliar learning content as more challenging. To address this issue, tailored software education according to the learners' characteristics is essential. Art students, for instance, with their strong visual comprehension and expressive abilities, can benefit from utilizing visual literacy to enhance the effectiveness of programming education. In this study, we propose decomposing everyday problems into flowcharts and pseudocode to construct procedural and visual images. Using the educational programming language PlayBot, we aim to analyze the effectiveness of teaching by coding to solve problems. Through this approach, students are expected to grasp programming concepts, understand problem-solving processes through computational thinking, and acquire skills to apply programming in their respective fields.