IJIET 2025 Vol.15(12): 2770-2780
doi: 10.18178/ijiet.2025.15.12.2471
doi: 10.18178/ijiet.2025.15.12.2471
Teaching Neural Networks to Computer Science Students in Higher Education: Approaches and Challenges
Meruyert Serik1, Nurzhanar Karilkhan1,*, Jaroslav Kultan2, and Dashzhan Narodkhan3
1. Computer Science Department, Faculty of Information Technology, L.N. Gumilyov Eurasian National University, Astana, Kazakhstan
2. Department of Applied Informatics, University of Economics in Bratislava, Bratislava, Slovakia
3. Departments of the Mining Faculty, Mine aerology and a labor safety, Abylkas Saginov Karaganda Technical University, Karaganda, Kazakhstan
Email: serik_meruerts@mail.ru (M.S.); iskulai@gmail.com (N.K.); jaroslav.kultan@euba.sk (J.K.); dos_good@mail.ru (D.N.)
*Corresponding author
2. Department of Applied Informatics, University of Economics in Bratislava, Bratislava, Slovakia
3. Departments of the Mining Faculty, Mine aerology and a labor safety, Abylkas Saginov Karaganda Technical University, Karaganda, Kazakhstan
Email: serik_meruerts@mail.ru (M.S.); iskulai@gmail.com (N.K.); jaroslav.kultan@euba.sk (J.K.); dos_good@mail.ru (D.N.)
*Corresponding author
Manuscript received April 16, 2025; revised May 12, 2025; accepted August 18, 2025; published December 16, 2025
Abstract—Modern artificial Intelligence (AI) technologies are increasingly shaping higher education, particularly in their use in training computer science students and integrating neural networks into the learning process. The research aims to evaluate modern approaches and challenges to teaching neural networks to computer science students in higher education. This study employs a quasi-experimental method involving 85 third-year students enrolled in the Computer Science programs at L.N. Gumilyov Eurasian National University and Buketov Karaganda University. The participants were divided into two groups: an experimental group and a control group. The experimental group received instruction with an enhanced curriculum that included modern tools such as TensorFlow, Keras, OpenCV, and Google Colab. Data were collected through pre-tests and post-tests, evaluating changes in student motivation, content comprehension, and technical competencies. Pearson’s chi-square test was utilized to analyze the data, which revealed statistically significant improvements in the experimental group compared to the control group. These results suggest that integrating updated content and hands-on technologies into teaching practices enhances students’ skills and learning outcomes in neural network education. The revised neural network curriculum had a positive impact on student learning outcomes. The research emphasizes the importance of continually updating the curriculum to meet the evolving demands of modern AI.
Keywords—Artificial Intelligence (AI), machine learning, deep learning, neural networks, computer science education, AI tools, Python programming
Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
Keywords—Artificial Intelligence (AI), machine learning, deep learning, neural networks, computer science education, AI tools, Python programming
Cite: Meruyert Serik, Nurzhanar Karilkhan, Jaroslav Kultan, and Dashzhan Narodkhan, "Teaching Neural Networks to Computer Science Students in Higher Education: Approaches and Challenges," International Journal of Information and Education Technology, vol. 15, no. 12, pp. 2770-2780, 2025.
Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
Article Metrics in Dimensions
Next Paper
Last page