Explainable Artificial Intelligence Applied to the Teaching and Learning of Convolutional Neural Network Concepts
DOI:
https://doi.org/10.5753/rbie.2026.7253Keywords:
Artificial Intelligence, CNN, Computer Science Education, XAI, Higher EducationAbstract
This study investigates the potential of Explainable Artificial Intelligence (XAI) as a didactic resource for teaching Convolutional Neural Networks (CNN) in higher education. The main objective was to evaluate whether explanation techniques for deep learning models – such as Class Activation Maps and Feature Maps – can support students’ conceptual understanding. A comparative case study was conducted with 63 undergraduate students from two higher education institutions in Presidente Prudente, São Paulo state, Brazil (Fatec and Unesp). The experiment consisted of a lecture divided into two parts: the first presented CNN concepts using traditional visual materials, while the second incorporated XAI-based visualizations. A questionnaire administered at the end of each part allowed us to measure immediate learning gains. Results showed a significant increase in correct responses, particularly among students with less prior knowledge, and a high perception of XAI’s contribution to learning (over 90% agreement at Fatec and 73% at Unesp). The findings suggest that XAI visual resources enhance the teaching and learning process of CNN by making abstract concepts more accessible and engaging to students
Downloads
References
Azam, S., Montaha, S., Fahim, K. U., Rafid, A. K., Mukta, M. S., & Jonkman, M. (2023). Using Feature Maps to Unpack the CNN ‘Black Box’ Theory with Two Medical Datasets of Different Modality. Intelligent Systems with Applications, 18, p. 200233.
href="https://doi.org/10.1016/j.iswa.2023.200233">https://doi.org/10.1016/j.iswa.2023.200233 [GS Search]
Carter, S., Armstrong, Z., Schubert, L., Johnson, I., & Olah, C. (2019). Activation Atlas. Distill. Disponível em: [link]. [GS Search]
Chatterji, A., Cunningham, T., Deming, D. J., Hitzig, Z., Ong, C., Shan, C. Y., & Wadman, K. (2025). How People Use ChatGPT (Working Paper No. 34255). National Bureau of Economic Research. https://doi.org/10.3386/w34255 [GS Search]
Chiaburu, T., Haußer, F., & Bießmann, F. (2024). Confident Teacher, Confident Student? A Novel User Study Design for Investigating the Didactic Potential of Explanations and their Impact on Uncertainty. arXiv. Disponível em: [link]. [GS Search]
Dis, E. A., Bollen, J., Zuidema, W., Rooij, R. v., & Bockting, C. L. (2023). ChatGPT: Five Priorities for Research. Nature, 614(7947), pp. 224-226. https://doi.org/10.1038/d41586-023-00288-7 [GS Search]
Gildenblat, J. (2025). Advanced AI Explainability for PyTorch. Acesso em 26 de 05 de 2026. Disponível em: [link]. [GS Search]
Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. & Bengio, Y. (2014). Generative Adversarial Nets. 28th International Conference on Neural Information Processing Systems, 2, pp. 2672–2680. Cambridge. [GS Search]
Hao, H., Rui, W., Hao, L., & Huai, Y. (2024). UnionCAM: Enhancing CNN Interpretability Through Denoising, Weighted Fusion, and Selective High-Quality Class Activation Mapping. Frontiers in Neurorobotics, 18. https://doi.org/10.3389/fnbot.2024.1338149 [GS Search]
Kalasampath, K., Spoorthi, K. N., Sajeev, S., Kuppa, S. S., Ajay, K., & Maruthamuthu, A. (2025). A Literature Review on Applications of Explainable Artificial Intelligence (XAI). IEEE Access, 13, pp. 41111-41140. https://doi.org/10.1109/ACCESS.2025.3546681 [GS Search]
Khosravi, H., Shum, S. B., Chen, G., Conati, C., Tsai, Y.-S., Kay, J., . . . Gašević, D. (2022). Explainable Artificial Intelligence in Education. Computers and Education: Artificial Intelligence, 3, p. 100074. https://doi.org/10.1016/j.caeai.2022.100074 [GS Search]
McCarthy, J., Minsky, M. L., Rochester, N., & Shannon, C. E. (1955). A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence. Disponível em: [link]. [GS Search]
Martins, R. M., von Wangenheim, C. G., Rauber, M. F., & Hauck, J. C. R. (2023). Eficácia das Metodologias Ativas e do Suporte Tecnológico no Ensino de Machine Learning na Educação Básica. Anais do III Simpósio Brasileiro de Educação em Computação (EDUCOMP) (pp. 154–162). Sociedade Brasileira de Computação. https://doi.org/10.5753/educomp.2023.228162 [GS Search]
Naveed, S., Stevens, G., & Robin-Kern, D. (2024). An Overview of the Empirical Evaluation of Explainable AI (XAI): A Comprehensive Guideline for User-Centered Evaluation in XAI. Applied Sciences, 14(23), p. 11288. https://doi.org/10.3390/app142311288 [GS Search]
Olah, C., Satyanarayan, A., Johnson, I., Carter, S., Schubert, L., Ye, K., & Mordvintsev, A. (2018). The Building Blocks of Interpretability. Distill. Disponível em: [link]. [GS Search]
Research, G. V. (2025). AI In Education Market Size, Share & Trends Analysis Report. San Francisco: Grand View Research. Disponível em: [link].
Saarela, M., & Podgorelec, V. (2024). Recent Applications of Explainable AI (XAI): A Systematic Literature Review. Applied Sciences, 14(19). https://doi.org/10.3390/app14198884 [GS Search]
Sanusi, I. T., & Oyelere, S. S. (2020). Pedagogies of Machine Learning in K-12 Context. Proceedings of the IEEE Frontiers in Education Conference (FIE), (pp. 1-8). https://doi.org/10.1109/FIE44824.2020.9274129 [GS Search]
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-cam: Visual Explanations from Deep Networks via Gradient-Based Localization. IEEE International Conference on Computer Vision, (pp. 618-626). Disponível em: [link]. [GS Search]
Turing, A. M. (1950). Computing Machinery and Intelligence. Mind, 59(236), pp. 433-460. https://doi.org/10.1093/mind/LIX.236.433 [GS Search]
Türkmen, G. (2024). The Review of Studies on Explainable Artificial Intelligence in Educational Research. Journal of Educational Computing Research, 63(2), pp. 277-310. https://doi.org/10.1177/07356331241310915 [GS Search]
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., . . . Polosukhin, I. (2017). Attention is All you Need. 31st International Conference on Neural Information Processing Systems, (pp. 6000–6010). Red Hook. Disponível em: [link]. [GS Search]
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Marcelo Buscioli Tenorio, Danilo Medeiros Eler
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
