DOI QR코드

DOI QR Code

Analysis and Orange Utilization of Training Data and Basic Artificial Neural Network Development Results of Non-majors

비전공자 학부생의 훈련데이터와 기초 인공신경망 개발 결과 분석 및 Orange 활용

  • Kyeong Hur (Department of Computer Education, Gyeong-In National University of Education)
  • 허경 (경인교육대학교 컴퓨터교육과)
  • Received : 2023.07.22
  • Accepted : 2023.08.10
  • Published : 2023.08.30

Abstract

Through artificial neural network education using spreadsheets, non-major undergraduate students can understand the operation principle of artificial neural networks and develop their own artificial neural network software. Here, training of the operation principle of artificial neural networks starts with the generation of training data and the assignment of correct answer labels. Then, the output value calculated from the firing and activation function of the artificial neuron, the parameters of the input layer, hidden layer, and output layer is learned. Finally, learning the process of calculating the error between the correct label of each initially defined training data and the output value calculated by the artificial neural network, and learning the process of calculating the parameters of the input layer, hidden layer, and output layer that minimize the total sum of squared errors. Training on the operation principles of artificial neural networks using a spreadsheet was conducted for undergraduate non-major students. And image training data and basic artificial neural network development results were collected. In this paper, we analyzed the results of collecting two types of training data and the corresponding artificial neural network SW with small 12-pixel images, and presented methods and execution results of using the collected training data for Orange machine learning model learning and analysis tools.

스프레드시트를 활용한 인공신경망 교육을 통해, 비전공자 학부생들은 인공신경망의 동작 원리을 이해하며 자신만의 인공신경망 SW를 개발할 수 있다. 여기서, 인공신경망의 동작 원리 교육은 훈련데이터의 생성과 정답 라벨의 할당부터 시작한다. 이후, 인공 뉴런의 발화 및 활성화 함수, 입력층과 은닉층 그리고 출력층의 매개변수들로부터 계산되는 출력값을 학습한다. 마지막으로, 최초 정의된 각 훈련데이터의 정답 라벨과 인공신경망이 계산한 출력값 간 오차를 계산하는 과정을 학습하고 오차제곱의 총합을 최소화하는 입력층과 은닉층 그리고 출력층의 매개변수들이 계산되는 과정을 학습한다. 스프레드시트를 활용한 인공신경망 동작 원리 교육을 비전공자 학부생 대상으로 실시하였다. 그리고 이미지 훈련데이터와 기초 인공신경망 개발 결과를 수집하였다. 본 논문에서는 12화소 크기의 소용량 이미지로 두 가지 훈련데이터와 해당 인공신경망 SW를 수집한 결과를 분석하고, 수집한 훈련데이터를 Orange 머신러닝 모델 학습 및 분석 도구에 활용하는 방법과 실행 결과를 제시하였다.

Keywords

References

  1. Korea Ministry of Education, "Education policy direction and core tasks in the age of artificial intelligence," Report Material, 2020. 
  2. Korea Ministry of Education, "Ministry of Education Active Administration Action Plan," Report Material, 2020. 
  3. Korea Ministry of Education, "The standard of artificial intelligence for elementry, middle and high school students," Report Material, 2020. 
  4. W. S. Son, "Development of SW education class plan using artificial intelligence," Journal of the Korean Association of Information Education, vol. 24, no. 5, pp. 453-462, 2020.  https://doi.org/10.14352/jkaie.2020.24.5.453
  5. Lee, J. and Lee, S., "A study on experts' perception survey on elementary AI education platform," Journal of The Korean Association of Information Education, vol. 24, no. 5, pp. 483-494, 2020.  https://doi.org/10.14352/jkaie.2020.24.5.483
  6. L. S. R. Park and Y. S. Kim, "Artificial intelligence education method in elementary school using AI education platform," Proceeding of the Korean Association of Computer Education, vol. 24, no. 2, 187-190, 2020. 
  7. J. H. Kim, "Development of an AI education program based on novel engineering for elementary school students," Master Thesis from Seoul National University of Education, 2020. 
  8. K. Hur, "An educational case study of image recognition principle in artificial neural networks for teacher educations," Journal of the Korean Association of Information Education, vol. 25, no. 5, pp. 791-801, 2021.  https://doi.org/10.14352/jkaie.2021.25.5.791
  9. Orange, University of Ljubljana, 2023, [Online]. Available: https://orangedatamining.com/.