Informatics and Applications
2024, Volume 18, Issue 2, pp 72-81
ON THE APPLICATION OF GENERATIVE MODELS IN THE E-LEARNING SYSTEM OF MATHEMATICAL DISCIPLINES
Abstract
The existing tools for individual learning trajectory dynamic design are complemented by the generating technology of certification tasks and exam tickets. A set of exam tickets specially prepared by experts in the university course of the theory of functions of a complex variable was used as a source of high-quality, balanced sets of tasks. This significant training array of high-quality attestation tasks has significantly expanded the available data created at previous stages. The purpose ofthe performed research was to create methods that allow taking into account the experts' knowledge embedded in the available set oftasks. The implemented generation model when processing educational content uses as parameters the attributes assigned by experts to tasks: topic, complexity, and formed competencies. Two generation methods are proposed. The first one, probabilistic, uses only the frequency characteristics of the training set, approximating the probability distribution. The second one is based on generative-adversarial neural networks. Particular attention is paid to the discussion of the difficulties of the network implementation, including those related to the specific nature ofthe generative model.
[+] References (26)
- Rasch, G. 1980. Probabilistic models for some intelligence and attainment tests. Chicago, IL: University of Chicago Press. 224 p.
- Van der Linden, W.J., D.J. Scrams, and D. L. Schnipke. 1999. Using response-time constraints to control for differential speededness in computerized adaptive testing. Appl. Psych. Meas. 23(3):195-210. doi: 10.1177/ 01466219922031329.
- Chen, C.-M., H.-M. Lee, and Y.-H. Chen. 2005. Personalized e-learning system using Item Response Theory. Computers Education 44(3):237-255. doi: 10.1016/ j.compedu.2004.01.006.
- Kibzun, A. I., and A. O. Inozemtsev. 2014. Using the maximum likelihood method to estimate test complexity levels. Automat. Rem. Contr. 75(4):607-621. doi: 10.1134/S000511791404002X. EDN: SKRJCX.
- Kuravsky, L. S., A. A. Margolis, P.A. Marmalyuk, A. S. Panfilova, G. A. Yuryev, and P. N. Dumin. 2016. A probabilistic model of adaptive training. Applied Mathematical Sciences 10(48):2369-2380. doi: 10.12988/ ams.2016.65168.
- Naumov, A. V., and G. A. Mkhitaryan. 2016. On the problem of probabilistic optimization of time-limited testing. Automat. Rem. Contr. 77(9):1612-1621. doi: 10.1134/ S0005117916090083. EDN: XFMWHF.
- Bosov, A. V., G. A. Mkhitaryan, A. V. Naumov, and A. P. Sapunova. 2019. Ispol'zovanie modeli gamma- raspredeleniya v zadache formirovaniya ogranichennogo po vremeni testa v sisteme distantsionnogo obucheniya [Using the model of gamma distribution in the problem of forming a time-limited test in a distance learning system]. Informatika ieePrimeneniya - Inform. Appl. 13(4):12-18. doi: 10.14357/19922264190402. EDN: XUBLZX.
- Bosov, A. V., Ya. G. Martyushova, A.V. Naumov, and A. P. Sapunova. 2020. Bayesovskiy podkhod k postroeniyu individual'noy traektorii pol'zovatelya v sisteme distantsionnogo obucheniya [Bayesian approach to the construction ofan individual user trajectory in the system of distance learning]. Informatika i ee Primeneniya - Inform. Appl. 14(3):89-96. doi: 10.14357/19922264200313. EDN: WAKFJR.
- Adomavicius, G., and A. Tuzhilin. 2005. Toward the next generation of recommender systems: A survey of the state- of-the-art and possible extensions. IEEE T. Knowl. Data En. 17(6):734-749. doi: 10.1109/TKDE.2005.99.
- Verbert, K., N. Manouselis, X. Ochoa, M. Wolpers, H. Drachsler, I. Bosnic, and E. Duval. 2012. Context- aware recommender systems for learning: A survey and future challenges. IEEE T. Learn. Technol. 5(4):318–335. doi: 10.1109/TLT.2012.11.
- Bosov, A.V 2022. Primenenie samoorganizuyushchikhsya neyronnykh setey k protsessu formirovaniya individual'noy traektorii obucheniya [Application of selforganizing neural networks to the process of forming an individual learning path]. Informatika i ee Primeneniya - Inform. Appl. 16(3):7-15. doi: 10.14357/19922264220302. EDN: HJQANN.
- Tai, D.WS., H.J. Wu, and P.H. Li. 2008. Effective e-learning recommendation system based on selforganizing maps and association mining. Electron. Libr. 26(3):329-344.
- Bhaskaran, S., R. Marappan, and B. Santhi. 2021. Design and analysis of a cluster-based intelligent hybrid recommendation system for e-learning applications. Mathematics 9:197. 21 p. doi: 10.3390/math9020197.
- Harshvardhan, G.M., M.K. Gourisaria, M. Pandey, and S. S. Rautaray. 2020. A comprehensive survey and analysis of generative models in machine learning. Computer Science Review 38:100285. 29 p. doi: 10.1016/j.cosrev.2020.100285.
- Bosov, A. V., and A.V. Ivanov. 2022. Tekhnologiya klassifikatsii tipov kontenta elektronnogo uchebnika [Technology for classification of content types of e-textbooks]. Informatika i ee Primeneniya - Inform. Appl. 16(4):63-72. doi: 10.14357/19922264220410. EDN: YERCNH.
- Bosov, A. V., and A. V. Ivanov. 2023. Tekhnologiya mnogofaktornoy klassifikatsii matematicheskogo kontenta elektronnoy sistemy obucheniya [Multifactor classification technology of mathematical content of e-learning system]. Informatika i ee Primeneniya - Inform. Appl. 17(4):32-41. doi: 10.14357/19922264230405. EDN: LISHHZ.
- Bityukov, Yu. I., and Ya. G. Martyushova. 2022. Reshenie zadach po teorii funktsiy kompleksnogo peremennogo [Solving problems on the theory of functions of a complex variable]. Moscow: MAI. 87 p.
- Goodfellow, I., J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, and Y. Bengio. 2014. Generative adversarial nets. Adv. New. Inf. 27(3):2672-2680. doi: 10.1007/978-3-658-40442-0_9.
- Chollet, F. 2021. Deep learning with Python. 2nd ed. Shelter Island, NY: Manning. 504 p.
- Maas, A. L., A. Y. Hannun, and A. Y. Ng. 2013. Rectifier nonlinearities improve neural network acoustic models. Proc.ICML 30(1):3. 6 p.
- Arjovsky M., and L. Bottou. 2017. Towards principled methods for training generative adversarial networks. Cornell University. 17 p. Available at: https://arxiv.org/ abs/1701.04862 (accessed May 6, 2024).
- Saatci, Y., and A. G. Wilson. 2017. Bayesian GAN. Cornell University 16 p. Available at: https://arxiv.org/ abs/1705.09558 (accessed May 6, 2024).
- Glorot, X., and Y. Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. J. Mach. Learn. Res. 9:249-256.
- He, K., X. Zhang, S. Ren, and J. Sun. 2015. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. Conference (International) on Computer Vision Proceedings. Piscataway, NJ: IEEE. 1026-1034. doi: 10.1109/ICCV.2015.123.
- Srivastava, N., G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. 2014. Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(56):1929-1958.
- Kullback, S., and R.A. Leibler. 1951. On information and sufficiency. Ann. Math. Stat. 22(1):79–86. doi: 10.1214/aoms/1177729694.
[+] About this article
Title
ON THE APPLICATION OF GENERATIVE MODELS IN THE E-LEARNING SYSTEM OF MATHEMATICAL DISCIPLINES
Journal
Informatics and Applications
2024, Volume 18, Issue 2, pp 72-81
Cover Date
2024-06-20
DOI
10.14357/19922264240210
Print ISSN
1992-2264
Publisher
Institute of Informatics Problems, Russian Academy of Sciences
Additional Links
Key words
e-learning system; educational content; machine learning; generative models; computer simulation; generative-adversarial networks
Authors
A. V. Bosov  and A. V. Ivanov
Author Affiliations
Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences, 44-2 Vavilov Str., Moscow 119333, Russian Federation
|