Interdisciplinary Case Design and Exploration for Machine Learning Course

Authors

  • Guangmei Xu College of Smart City, Beijing Union University, Beijing, 100101, China
  • Jinhua Wang College of Smart City, Beijing Union University, Beijing, 100101, China
  • Jingzun Zhang College of Smart City, Beijing Union University, Beijing, 100101, China
  • Ning He College of Smart City, Beijing Union University, Beijing, 100101, China

DOI:

https://doi.org/10.54097/az1f2330

Keywords:

Machine Learning, Dunhuang Images, Interdisciplinarity, Case Design

Abstract

Traditional machine learning teaching commonly suffers from repetitive experimental paradigms and narrow real-world application contexts, which leads students to rely on mechanical code replication and surface-level learning. This instructional pattern fails to cultivate interdisciplinary cognition and humanistic accomplishment. To improve the current teaching deficiencies, this study adopts digitized Dunhuang mural resources as an innovative teaching medium to develop interdisciplinary practice cases. Following the design concepts of staged ability progression, integration of technical and artistic perspectives, and authentic scenario orientation, this research constructs a three-tier teaching system including basic training, in-depth exploration and comprehensive innovation. The practical curriculum covers a full range of computer vision tasks: Dunhuang image preprocessing, stylistic discrimination, CNN visual recognition, artistic style migration, decorative pattern generation, and damaged mural inpainting. All experimental units combine algorithm engineering practice with Dunhuang art and cultural instruction. This study develops two-dimensional teaching support resources. It also constructs a tailored T-A-P evaluation system that integrates technical ability, artistic attainment and practical performance. The comprehensive student assessment covers coding skills, model error analysis and cultural aesthetic understanding. Classroom teaching practice has proven that the designed case system can significantly strengthen students’ machine learning engineering capabilities and enrich their cultural accomplishment. This research offers a feasible and referable paradigm for interdisciplinary integration in artificial intelligence teaching.

Downloads

Download data is not yet available.

References

[1] Wan, L., Liu, J., & Chen, Y. (2022). Practical teaching reform of machine learning courses under the background of Emerging Engineering Education. Computer Education, (5), 145–149. (in Chinese)

[2] Sun, J., Lu, L., Wang, X., et al. (2026). Collaborative education innovation and practice in data mining and machine learning courses. Industry and Information Technology Education, (8), 55–59. (in Chinese)

[3] Li, M., Liang, C., Wang, M., et al. (2026). Practical exploration of the course construction of "Machine Learning and Data Mining" based on multi-dimensional and multi-disciplinary cross-integration. Forestry Education in China, 44(4), 122–128. (in Chinese)

[4] Wang, Y., Xiong, Q., Gao, M., et al. (2025). Teaching reform of machine learning under the background of large models. Computer Education, (11), 136–141. (in Chinese)

[5] Jiang, Y. (2024). Exploration of machine learning course teaching based on the "1-2-3-4" teaching method. Computer Education, (10), 229–234. (in Chinese)

[6] Yin, L., & Liu, Z. (2025). Teaching reform to improve students' practical ability in machine learning courses based on industry-education integration. Computer Education, (4), 156–161. (in Chinese)

[7] Liu, J., Zhu, J., Duan, G., et al. (2025). Construction of an industry-oriented cross-application case base for machine learning courses. Computer Education, (3), 271–276. (in Chinese)

[8] Tang, J., Wang, Y., Wang, M., et al. (2024). Machine learning curriculum reform and practice based on the "3M" teaching method. Computer Education, (1), 97–102. (in Chinese) DOI: https://doi.org/10.62381/H241C17

[9] Zeng, Y. (2022). Exploration of innovative practice in teaching machine learning courses under the background of new engineering. Computer Education, (11), 78–81. (in Chinese)

[10] Ying, Y., Ren, K., & Li, X. (2021). Construction of artificial intelligence module course for applied undergraduate new engineering majors. Intelligent Computers and Applications, 11(10), 131–133. (in Chinese)

[11] Li, J., Wei, Y., Wu, Y., et al. (2022). Progressive experimental case design in machine learning courses. Computer Education, (1), 134–138. (in Chinese)

[12] Yang, S. (2026). Research on the innovative application of Dunhuang mural elements in graphic creative design teaching. Calligraphy, Painting and Poetry, (3), 140–141. (in Chinese)

[13] Duan, W. (2026). Artistic characteristics of Dunhuang murals and their inspiration for contemporary painting: Taking the murals of Mogao Cave 428 as an example. New Legends, (22), 50–52. (in Chinese)

Downloads

Published

20-10-2026

Issue

Section

Articles

How to Cite

Xu, G., Wang, J., Zhang, J., & He, N. (2026). Interdisciplinary Case Design and Exploration for Machine Learning Course. Journal of Education and Educational Research, 21(2), 23-27. https://doi.org/10.54097/az1f2330