Modelo predictivo usando Redes Neuronales de Boltzmann para el análisis del rendimiento a partir de los informes de cierre presentados por los docentes
| dc.contributor.advisor | Gomez Vasco, Carlos Andres | |
| dc.contributor.author | Ramirez Cabrera, Daniel Felipe | |
| dc.contributor.author | Criollo Bermúdez, Santiago | |
| dc.contributor.orcid | Gomez Vasco, Carlos Andres [0000-0003-1473-0568] | |
| dc.creator.email | danielpiperc05@gmail.com | |
| dc.creator.email | santicriollo@hotmail.com | |
| dc.creator.id | 20211107006 | |
| dc.creator.id | 20202107022 | |
| dc.date.accessioned | 2026-04-16T15:33:02Z | |
| dc.date.available | 2026-04-16T15:33:02Z | |
| dc.date.created | 2026-03-20 | |
| dc.description | Este trabajo de grado presenta NeuroCampus, un software de analítica predictiva basado en Redes Neuronales de Boltzmann para analizar el rendimiento docente a partir de los informes de cierre y las evaluaciones históricas del Departamento de Química de la Universidad Pedagógica Nacional. La propuesta integra principios de física estadística, aprendizaje automático y procesamiento de lenguaje natural en una arquitectura reproducible con backend en FastAPI y frontend en React, capaz de transformar calificaciones y comentarios en variables operativas para apoyar la toma de decisiones académicas. En el desarrollo se implementaron modelos BM, RBM y DBM, junto con un pipeline de ingesta, validación, estandarización, construcción de características, análisis de sentimiento y generación de reportes. Los resultados muestran que el sistema permite auditar el ciclo completo desde el dato crudo hasta los indicadores agregados, mejorar la trazabilidad del proceso y ofrecer estimaciones útiles sobre desempeño esperado, riesgos potenciales y comparaciones por docente, asignatura y periodo. | |
| dc.description.abstract | This undergraduate thesis presents NeuroCampus, a predictive analytics software based on Boltzmann Neural Networks to analyze teaching performance from closing reports and historical evaluation data from the Chemistry Department at Universidad Pedagógica Nacional. The proposal integrates principles of statistical physics, machine learning, and natural language processing into a reproducible architecture with a FastAPI backend and a React frontend, capable of transforming grades and comments into operational variables that support academic decision-making. The development included BM, RBM, and DBM models, together with a pipeline for data ingestion, validation, standardization, feature construction, sentiment analysis, and report generation. The results show that the system makes it possible to audit the complete cycle from raw data to aggregated indicators, improve process traceability, and provide useful estimates of expected performance, potential risks, and comparisons by lecturer, subject, and academic period. | |
| dc.format.mimetype | ||
| dc.identifier.uri | http://hdl.handle.net/11349/101058 | |
| dc.language.iso | spa | |
| dc.publisher | Universidad Distrital Francisco José de Caldas | |
| dc.relation.references | Ackley, D. H., Hinton, G. E., y Sejnowski, T. J. (1985). A learning algorithm for Boltzmann machines. Cognitive Science, 9(1), 147–169. | |
| dc.relation.references | Bengio, Y., & Delalleau, O. (2009). Justifying and generalizing contrastive divergence. Neural computation, 21(6), 1601-1621. | |
| dc.relation.references | Carreira-Perpinan, M. A., & Hinton, G. (2005, January). On contrastive divergence learning. In International workshop on artificial intelligence and statistics (pp. 33-40). PMLR. | |
| dc.relation.references | Chen, T. (2024). A study on the improvement of student education management in universities based on depth-constrained Boltzmann machine. Applied Mathematics and Nonlinear Sciences, 9(1). https://doi.org/10.2478/amns.2023.2.00928 | |
| dc.relation.references | Fischer, A., & Igel, C. (2010, September). Empirical analysis of the divergence of Gibbs sampling based learning algorithms for restricted Boltzmann machines. In International conference on artificial neural networks (pp. 208-217). Berlin, Heidelberg: Springer Berlin Heidelberg. | |
| dc.relation.references | Fischer, A., & Igel, C. (2012, September). An introduction to restricted Boltzmann machines. In Iberoamerican congress on pattern recognition (pp. 14-36). Berlin, Heidelberg: Springer Berlin Heidelberg. | |
| dc.relation.references | Fischer, A., & Igel, C. (2014). Training restricted Boltzmann machines: An introduction. Pattern Recognition, 47(1), 25-39. | |
| dc.relation.references | Hinton, G. (2010). A practical guide to training restricted Boltzmann machines. Momentum, 9(1), 926. | |
| dc.relation.references | Hinton, G. E. (2002). Training products of experts by minimizing contrastive divergence. Neural Computation, 14(8), 1771–1800. | |
| dc.relation.references | Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the dimensionality of data with neural networks. science, 313(5786), 504-507. | |
| dc.relation.references | Hinton, G. E., Sejnowski, T. J., & Ackley, D. H. (1984). Boltzmann machines: Constraint satisfaction networks that learn. | |
| dc.relation.references | Hinton, G. E., & Sejnowski, T. J. (1986). Learning and relearning in Boltzmann machines. Parallel distributed processing: Explorations in the microstructure of cognition, 1(282-317), 2. | |
| dc.relation.references | Hopfield, J. J. (1982). Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences, 79(8), 2554–2558. | |
| dc.relation.references | Larochelle, H., & Bengio, Y. (2008, July). Classification using discriminative restricted Boltzmann machines. In Proceedings of the 25th international conference on Machine learning (pp. 536-543). | |
| dc.relation.references | LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. nature, 521(7553), 436-444. | |
| dc.relation.references | Le Roux, N., & Bengio, Y. (2008). Representational power of restricted Boltzmann machines and deep belief networks. Neural computation, 20(6), 1631- 1649. | |
| dc.relation.references | Li, Q. (2021). The use of artificial intelligence combined with cloud computing in the design of education information management platform. International Journal of Emerging Technologies in Learning (iJET), 16(5), 32-44. | |
| dc.relation.references | Nair, V., & Hinton, G. E. (2008). Implicit mixtures of restricted Boltzmann machines. Advances in neural information processing systems, 21. | |
| dc.relation.references | Nobel Committee for Physics. (2024, 8 de octubre). Scientific background to the Nobel Prize in Physics 2024: ”For foundational discoveries and inventions that enable machine learning with artificial neural networks”. The Royal Swedish Academy of Sciences. | |
| dc.relation.references | Rosenblatt, F. (1958). The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 65(6), 386–408. | |
| dc.relation.references | Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1985). Learning internal representations by error propagation (No. ICS8506). | |
| dc.relation.references | Salakhutdinov, R. (2008). Learning and evaluating Boltzmann machines. Utml Tr, 2, 21. | |
| dc.relation.references | Salakhutdinov, R., y Hinton, G. (2009). Deep Boltzmann machines. En D. van Dyk y M. Welling (Eds.), Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics (Vol. 5, pp. 448–455). PMLR. | |
| dc.relation.references | Smolensky, P. (1986). Information processing in dynamical systems: Foundations of harmony theory (No. CUCS32186). | |
| dc.relation.references | Teh, Y. W., Welling, M., Osindero, S., & Hinton, G. E. (2003). Energy-based models for sparse overcomplete representations. Journal of Machine Learning Research, 4(Dec), 1235-1260. | |
| dc.relation.references | Tieleman, T. (2008, July). Training restricted Boltzmann machines using approximations to the likelihood gradient. In Proceedings of the 25th international conference on Machine learning (pp. 1064-1071). | |
| dc.relation.references | Welling, M., & Hinton, G. E. (2002, August). A new learning algorithm for mean field Boltzmann machines. In International conference on artificial neural networks (pp. 351-357). Berlin, Heidelberg: Springer Berlin Heidelberg. | |
| dc.relation.references | Williams, C. K., & Agakov, F. V. (2002). An analysis of contrastive divergence learning in Gaussian Boltzmann machines. Institute for Adaptive and Neural Computation. | |
| dc.relation.references | Xu, B., Song, S., & Wang, D. (2020). Application of smart safety training and education in network teaching management. Safety science, 124, 104608. | |
| dc.relation.references | Yuille, A. L. (2004). The convergence of contrastive divergences. Advances in neural information processing systems, 17. | |
| dc.rights.acceso | Abierto (Texto Completo) | |
| dc.rights.accessrights | OpenAccess | |
| dc.subject | Redes de Boltzmann | |
| dc.subject | Física Estadística | |
| dc.subject | Aprendizaje Automático | |
| dc.subject | Evaluación Docente | |
| dc.subject | Ciencia de datos | |
| dc.subject.keyword | Boltzmann Networks | |
| dc.subject.keyword | Statistical Physics | |
| dc.subject.keyword | Machine Learning | |
| dc.subject.keyword | Teaching Evaluation | |
| dc.subject.keyword | Data Science | |
| dc.subject.lemb | Física -- Tesis y disertaciones académicas | |
| dc.subject.lemb | Redes neuronales — Aplicaciones educativas | |
| dc.subject.lemb | Aprendizaje automático — Modelos predictivos | |
| dc.subject.lemb | Rendimiento académico — Evaluación | |
| dc.title | Modelo predictivo usando Redes Neuronales de Boltzmann para el análisis del rendimiento a partir de los informes de cierre presentados por los docentes | |
| dc.title.titleenglish | A predictive model using Boltzmann neural networks to analyze performance based on end-of-term reports submitted by teachers | |
| dc.type | bachelorThesis | |
| dc.type.coar | http://purl.org/coar/resource_type/c_7a1f | |
| dc.type.degree | Pasantía | |
| dc.type.driver | info:eu-repo/semantics/bachelorThesis |
Archivos
Bloque de licencias
1 - 1 de 1
Cargando...
- Nombre:
- license.txt
- Tamaño:
- 7 KB
- Formato:
- Item-specific license agreed upon to submission
- Descripción: