Design of a multilayer neural network in only two rows of an Excel spreadsheet for students without advanced programming knowledge
DOI:
https://doi.org/10.61467/2007.1558.2026.v17i4.1386Keywords:
Artificial Neural network, Backpropagation algorithm, Excel spreadsheet, GradientsAbstract
Artificial neural networks (ANNs) are intelligent techniques used as classification, prediction, or pattern recognition elements. It is necessary to have advanced programming knowledge to develop an artificial neural network using the Backpropagation (BP) learning algorithm. This research proposes the development of a multilayer neural network using the BP algorithm in only two rows of an Excel spreadsheet for students without advanced programming knowledge. The first row: the forward propagation of the network and the calculation of gradients in a simple manner. Each calculation is made in a specific cell. In the second row, the error is propagated backwards using the Backpropagation algorithm, adjusting the weights and biases of the output and hidden layers by subtracting the product of the two gradients. Once the correct filling of the two rows is complete, the data from the first and second rows is selected and dragged to the desired number of iterations in an easy, clear, and simple way, so that anyone without programming knowledge can develop a multilayer neural network. The tool does not require installation and offers a portable solution for designing neural networks for engineering students or students in any degree program without advanced programming knowledge. This methodology has been taught to 10 bachelor's and master´s groups in business management at the University of Guanajuato, resulting in 11 articles published in peer-reviewed journals, 3 bachelor’s theses, and 4 master’s theses.
Spanish-language metadata / Metadatos en español
Título en español:
Diseño de una red neuronal multicapa en solo dos filas de una hoja de cálculo de Excel para estudiantes sin conocimientos avanzados de programación
Resumen:
Las redes neuronales artificiales (RNA) son técnicas inteligentes utilizadas para tareas de clasificación, predicción y reconocimiento de patrones. Por lo general, el desarrollo de una red neuronal artificial mediante el algoritmo de aprendizaje por retropropagación requiere conocimientos avanzados de programación. Esta investigación propone el desarrollo de una red neuronal multicapa con el algoritmo de retropropagación en solo dos filas de una hoja de cálculo de Excel, dirigida a estudiantes sin conocimientos avanzados de programación.
En la primera fila se realiza la propagación hacia adelante de la red y el cálculo simplificado de los gradientes. Cada operación se lleva a cabo en una celda específica. En la segunda fila, el error se propaga hacia atrás mediante el algoritmo de retropropagación, ajustando los pesos y los sesgos de las capas de salida y ocultas mediante la sustracción del producto de los gradientes correspondientes.
Una vez completado correctamente el llenado de las dos filas, los datos de ambas se seleccionan y se arrastran hasta alcanzar el número deseado de iteraciones. Este procedimiento permite desarrollar una red neuronal multicapa de manera sencilla, clara y accesible, incluso para personas sin conocimientos de programación.
La herramienta no requiere instalación y ofrece una solución portátil para el diseño de redes neuronales dirigida a estudiantes de ingeniería o de cualquier programa académico que no cuenten con conocimientos avanzados de programación. Esta metodología se ha enseñado a diez grupos de licenciatura y maestría en gestión empresarial de la Universidad de Guanajuato, lo que ha derivado en 11 artículos publicados en revistas arbitradas, tres tesis de licenciatura y cuatro tesis de maestría.
Palabras Claves:
red neuronal artificial; algoritmo de retropropagación; hoja de cálculo de Excel; gradientes.
Smart citations:
https://scite.ai/reports/10.61467/2007.1558.2026.v17i4.1386
Dimensions.
Open Alex.
References
Bautista-Capetillo, C., Robles Rovelo, C. O., González-Trinidad, J., Pineda-Martínez, H., Júnez-Ferreira, H. E., & García-Bandala, M. (2023). Teaching sprinkler irrigation engineering by a spreadsheet tool. Water, 15(9), Article 1685. https://doi.org/10.3390/w15091685
Cao, W., Wang, X., Ming, Z., & Gao, J. (2018). A review on neural networks with random weights. Neurocomputing, 275, 278–287. https://doi.org/10.1016/j.neucom.2017.08.040
Chen, J., Yin, H., Zhang, K., Ren, Y., & Zeng, H. (2025). Integration of neural networks in brain–computer interface applications: Research frontiers and trend analysis based on Python. Engineering Applications of Artificial Intelligence, 151, Article 110654. https://doi.org/10.1016/j.engappai.2025.110654
Faria, A., & Miranda, G. L. (2026). Operationalising CTT and IRT in spreadsheets: A methodological demonstration for classroom assessment. Analytics, 5(1), Article 12. https://doi.org/10.3390/analytics5010012
Guerriero, V. (2023). Maximum likelihood instead of least squares in fracture analysis by means of a simple Excel sheet with VBA macro. Geosciences, 13(12), Article 379. https://doi.org/10.3390/geosciences13120379
Guo, R., Li, R., Ding, J., Wen, L., Zhang, Y., Wen, C., & Jiao, M. (2026). Neural network for gas recognition based on MOS electronic nose: Algorithm design and hardware deployment. Microchemical Journal, 225, Article 118008. https://doi.org/10.1016/j.microc.2026.118008
Kiran, Y. M., & Srinivas, S. (2021). Simple approach to model photovoltaic module using Solver utility of Microsoft Excel. In 2021 IEEE International Power and Renewable Energy Conference (IPRECON) (pp. 1–5). IEEE. https://doi.org/10.1109/IPRECON52453.2021.9640780
Lee, J., Yoon, Y., & Geem, Z. W. (2025). ANN-Excel: Artificial neural network framework in Excel. SoftwareX, 32, Article 102428. https://doi.org/10.1016/j.softx.2025.102428
Li, J. (2025). Entrepreneurial skill augmented neural network (ESANN): A deep learning approach for enhancing entrepreneurial competencies in teachers. International Journal of Computational Intelligence Systems, 18, Article 127. https://doi.org/10.1007/s44196-025-00851-2
Liu, J., González-Fernández, D., Castillo-Cara, M., & García-Castro, R. (2025). TINTOlib: A Python library for transforming tabular data into synthetic images for deep neural networks. SoftwareX, 32, Article 102444. https://doi.org/10.1016/j.softx.2025.102444
Lou, Y., & Li, F. (2024). Design of an online education student learning status evaluation model based on dual-improved neural networks. Intelligent Systems with Applications, 22, Article 200370. https://doi.org/10.1016/j.iswa.2024.200370
Nagy, T., Csernoch, M., & Biró, P. (2021). The comparison of students’ self-assessment, gender, and programming-oriented spreadsheet skills. Education Sciences, 11(10), Article 590. https://doi.org/10.3390/educsci11100590
Pinto, A. S., Abreu, A., Costa, E., & Paiva, J. (2023). How machine learning (ML) is transforming higher education: A systematic literature review. Journal of Information Systems Engineering and Management, 8(2), Article 21168. https://doi.org/10.55267/iadt.07.13227
Sun, X., & Zhang, Y. (2022). An improved BP neural network algorithm for the evaluation system of innovation and entrepreneurship education in colleges and universities. Mobile Information Systems, 2022, Article 1007538. https://doi.org/10.1155/2022/1007538
Tian, J. (2025). A practice-oriented computational thinking framework for teaching neural networks to working professionals. AI, 6(7), Article 140. https://doi.org/10.3390/ai6070140
White, J. C., & Lucci, F. (2026). ARMADILLO_VolcaNorm: An open-source, macro-enabled VBA for Excel™ spreadsheet for calculation of CIPW norms and IUGS igneous rock classification for volcanic rocks. Journal of South American Earth Sciences, 174, Article 106002. https://doi.org/10.1016/j.jsames.2026.106002
Wu, Z., Wang, Y., & Long, X. (2025). Reform path and empirical exploration of visual communication design education based on graph neural network. Systems and Soft Computing, 7, Article 200413. https://doi.org/10.1016/j.sasc.2025.200413
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Combinatorial Optimization Problems and Informatics
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
