An Educational Case Study of Image Recognition Principle in Artificial Neural Networks for Teacher Educations

교사교육을 위한 인공신경망 이미지인식원리 교육사례연구

  • Hur, Kyeong (Dept. of Computer Education, Gyeongin National University of Education)
  • 허경 (경인교육대학교 컴퓨터교육과)
  • Received : 2021.09.23
  • Accepted : 2021.10.15
  • Published : 2021.10.29


In this paper, an educational case that can be applied as artificial intelligence literacy education for preservice teachers and incumbent teachers was studied. To this end, a case of educating the operating principle of an artificial neural network that recognizes images is proposed. This training case focuses on the basic principles of artificial neural network operation and implementation, and applies the method of finding parameter optimization solutions required for artificial neural network implementation in a spreadsheet. In this paper, we focused on the artificial neural network of supervised learning method. First, as an artificial neural network principle education case, an artificial neural network education case for recognizing two types of images was proposed. Second, as an artificial neural network extension education case, an artificial neural network education case for recognizing three types of images was proposed. Finally, the results of analyzing artificial neural network training cases and training satisfaction analysis results are presented. Through the proposed training case, it is possible to learn about the operation principle of artificial neural networks, the method of writing training data, the number of parameter calculations executed according to the amount of training data, and parameter optimization. The results of the education satisfaction survey for preservice teachers and incumbent teachers showed a positive response result of over 70% for each survey item, indicating high class application suitability.

본 논문은 예비교사와 현직교사를 위한 인공지능 소양 교육으로 적용할 수 있는 교육 사례를 연구하였다. 이를 위해, 이미지를 인식하는 인공신경망의 동작 원리를 교육하는 사례를 제안하였다. 본 교육 사례는 인공신경망 동작 및 구현의 기초 원리 교육에 초점을 맞추어, 인공신경망 구현에 필요한 매개변수 최적화 해들을 스프레드시트로 찾는 방법을 적용하였다. 본 논문에서는 지도학습 방식의 인공신경망에 초점을 맞추었다. 첫 번째로, 인공신경망 원리 교육 사례로서 2종 이미지를 인식하는 인공신경망 교육 사례를 제안하였다. 두번째로 인공신경망 확장 교육 사례로서 3종 이미지를 인식하는 인공신경망 교육 사례를 제안하였다. 마지막으로 인공신경망 교육 사례를 분석한 결과와 교육 만족도 분석 결과를 제시하였다. 제안한 교육 사례를 통해, 인공신경망 동작 원리, 학습 데이터 작성 방법, 학습 데이터양에 따라 실행되는 매개변수 계산 회수 그리고 매개변수 최적화에 대해 학습할 수 있다. 예비교사와 현직교사에 대한 교육 만족도 조사 결과는 각 조사 항목에 대해 모두 70%이상 긍정적인 응답 결과를 나타내어, 높은 수업 적용 적합성을 나타내었다.



  1. Korea Ministry of Education, (2020). Education policy direction and core tasks in the age of artificial intelligence.
  2. Korea Ministry of Education, (2020). Ministry of Education Active Administration Action Plan.
  3. Korea Ministry of Education, (2020). The standard of artificial intelligence for elementry, middle and high school students.
  4. W. S. Son., (2020). Development of SW education class plan using artificial intelligence. Journal of The Korean Association of Information Education, 24(5), 453-462.
  5. S. K. Shin., (2021). A Study on Experts' Perception Survey on Elementary AI Education Platform. Journal of The Korean Association of Information Education, 24(5), 483-494.
  6. L. S. R. Park and Y. S. Kim., (2020). Artificial Intelligence Education Method in Elementary School Using AI Education Platform, The Korean Association Of Computer Education, 24(2), 187-190.
  7. J. H. Kim., (2020). Development of an AI Education Program based on Novel Engineering for Elementary School Students, Master Thesis from Seoul National University of Education.
  8. Y. Bengio, I. Goodfellow and A. Courville, (2017), Deep learning, MIT Press.
  9. K. Hornik, M. Stinchcombe and H. White, (1989). Multilayer feedforward networks are universal approximators, Neural Networks, 2(5), pp. 359-366.
  10. M. Roodschild, J. Gotay Sardinas and A. will, (2020), A new approach for the vanishing gradient problem on sigmoid activation, Springer Nature, 351-360.
  11. V. Nair and G. Hinton, (2010), "Rectified Linear Units Improve Restricted Boltzmann Machines," International Conference on Machine Learning, 807-814.
  12. Y. Qin, X. Wang and J. Zou, (2018), "The optimized deep belief networks with improved logistic Sigmoid units and their application in fault diagnosis for planetary gearboxes of wind turbines," IEEE Transactions on Industrial Electronics, 66(5), 3814-3824.
  13. X. Wang, Y. Qin, Y. Wang, S. Xiang and H. Chen, (2019), ReLTanh: An activation function with vanishing gradient resistance for SAE-based DNNs and its application to rotating machinery fault diagnosis," Neurocomputing, 363, 88-98.
  14. S. Kong and M. Takatsuka, (2017), "Hexpo: A Vanishing-Proof Activation Function," International Joint Conference on Neural Networks, 2562-2567.
  15. Y. Wakui and S. Wakui, (2020), Deep Learning with Excel," Seongandang Press.
  16. Korea Foundation for Advancement of Science & Creativity, (2020). Report on Exploratory Research Issues on Artificial Intelligence Education Content System for Elementary and Secondary Schools.
  17. J. S. Shin., M. H. Jo., (2021). Development and Implementation of an Activity-Based AI Convergence Education Program for Elementary School Student. Journal of The Korean Association of Information Education, 25(3), 437-448.
  18. I. S. Jeon, S. J. Jun and K. S. Song, (2020). Teacher Training Program and Analysis of Teacher's Demands to Strengthen Artificial Intelligence Education, Journal of The Korean Associationof Information Education, 24(4), 279-289.
  19. S. Kim, S. Kim, M. Lee and H. Kim, (2020). Review on Artificial Intelligence Education for K-12 Students and Teachers, Journal of Korean Associationof Computer Education, 23(4), 1-11.
  20. M. Ryu and S. K. Han, (2019). AI Education Programs for Deep-Learning Concepts, Journal of The Korean Association of Information Education, 23(6), 583-590.
  21. K. Kim and et. al., (2020). Development a Standard Curriculum Model of Next-generation Software Education, Journal of The Korean Association of Information Education, 24(4), 337-367.