Neural Networks in Teaching Mathematics
https://doi.org/10.18384/2949-5067-2025-4-88-99
Abstract
Aim. The aim of this study is demonstration of the process of transitioning the use of digital capabilities in teaching mathematical disciplines from automation systems to intelligent assistants capable of interacting with students in a dialog mode.
Methodology. The analysis of scientific and educational literature devoted to the use of artificial intelligence in education, in particular the didactic aspects of integrating neural networks and assessing the effectiveness of their use in education. Modeling and designing a neural network model for student learning for automatic generation of assignments, explanations of problem solutions, and feedback organization.
Results. A variant of a neural network learning model for generating learning tasks, developing explanation techniques and implementing feedback is proposed using the example of studying the Taylor formula and its applications in a course on mathematical analysis by first-year university students.
Research implications. The practical significance lies in the development of methodological recommendations for teachers on organizing the procedure for interaction between students and an intelligent tutor in the course of independent learning activities to master the content of sections and topics of mathematical disciplines that cause the greatest frequency of difficulties in understanding the essence and significance of mathematical content.
Supporting agencies: The work was carried out on the basis of an order to carry out research and development work in accordance with Order No. Pr-1189 “On the results of the competition for grants from the Federal State University of Education in 2025” dated 07. 07. 2025
About the Authors
S. Zabelina
Federal State University of Education
Russian Federation
Russian Federation
Svetlana B. Zabelina, Cand. Sci. (Education), Assoc. Prof.
Department of Higher Algebra, Mathematical Analysis and Geometry
Moscow; Moscow Region; Lyubertsy
I. Pinchuk
Federal State University of Education
Russian Federation
Russian Federation
Irina A. Pinchuk, Cand. Sci. (Phys.-Math.), Assoc. Prof.
Department of Higher Algebra, Mathematical Analysis and Geometry
Moscow
L. Gritskova
Federal State University of Education
Russian Federation
Russian Federation
Lyudmila S. Gritskova, Assistant Lecturer
Department of Higher Algebra, Mathematical Analysis and Geometry
Moscow; Moscow Region; Chekhov
S. Shammai Irani
Federal State University of Education
Russian Federation
Russian Federation
Suzanna M. Shammai Irani, Postgraduate Student
Department of Higher Algebra, Mathematical Analysis and Geometry
Moscow; Moscow Region; Reutov
References
1. Abramov, V. I., Grinshkun, A. V., Eliseev, A. V., Korneva, N. S. & Suvorova, T. N. (2023). Artificial Intelligence in Education: Application Areas and Limitations. In: Modern {digital} didactics. Vol. 2. Moscow: LLC "A-Prior" publ., pp. 89–98 (in Russ.).
2. Holmes W., Bialik M. & Fadel Ch. (2022). Artificial Intelligence in Education: Prospects and Challenges for Teaching and Learning. Moscow: Alpina publ. (in Russ.).
3. Avetisyan, A. I. (2024). Artificial intelligence in the humanitarian field. Threats and opportunities. In: Herald of the Russian Academy of Sciences, 94 (7), 623–628. DOI: 10.31857/S0869587324070028 (in Russ.).
4. Sharath Kumar, C. R. & Praveena, K. B. (2023). SWOT analysis. In: International Journal of Advanced Research, 11 (09), 744–748. DOI: 10.21474/ijar01/17584.
5. Hutson, J. & Rains, T. J. (2024). Charting the AI Transition in Education and Business Environments. Navigating the Generative Inflection Point for Industry 4.0 Success. New York: Routledge.
6. Khin, M. S., Bognar, L. & Afari, E. (eds.) (2025). Future of Learning with Large Language Models Applications and Research in Education. New York: CRC Press.
7. Mukhametzyanov, I. I. & Pyrnova, O. A. (2024). Generating ideas and creative solutions using artificial intelligence. In: Digital Systems and Models: Theory and Practice of Design, Development, and Application: Proceedings of the National (with International Participation) Scientific and Practical Conference (Kazan, April 10–11, 2024). Kazan: Kazan State Power Engineering University publ., pp. 1039–1042 (in Russ.).
8. Zabelina, S. B., Pinchuk, I. A., Prodanets, A. V. & Gritskova, L. S. (2023). Digital didactics: designing a training session based on shared services. In: International Forum KAZAN DIGITAL WEEK – 2023 : Collection of Materials (Kazan, September 20–22, 2023). Kazan: Scientific Center for Children's Life Safet publ., pp. 778–785 (in Russ.).
9. Gritskova, L. S. & Pinchuk, I. A. (2024). Using neural networks as an auxiliary tool in training. In: Problems of the theory and practice of innovative development and integration of modern science and education : Proceedings of the V International scientific and practical conference (Moscow, February 14, 2024). Moscow: LLC "PRINTIKA" publ., pp. 107–111 (in Russ.).
10. Pomerantz, J. & Brown, M. (2022). A study of personalization of learning and adaptive technologies: current use, implementation, and design. In: EDUCAUSE Review, 57 (2), 28–41.
11. Vidivelli, S., Manikandan, R. & Dharunbalaji, A. (2024). Efficiency-Driven Custom Chatbot Development: Unleashing LangChain, RAG, and Performance-Optimized LLM Fusion. In: Computers, Materials and Continua, 80 (2), 2423–2442. DOI: 10.32604/cmc.2024.054360.
12. Brovka, N. V. (2023). Artificial intelligence in teaching students of mathematical specialties: problems or prospects? In: Modern {digital} didactics. Vol. 2. Moscow: LLC "A-Prior" publ., pp. 56–62 (in Russ.).
Review
Views:
120
JATS XML
Email this article 