PROSPECTS FOR THE USE OF NEURAL NETWORKS IN TEACHER EDUCATION

The conditions necessary for the functioning of artificial intelligence are given. The basic rules for successfully conducting educational activities are defined. Groups of mathematical methods for data mining are presented. The effectiveness of using modern methods of Data Mining, Big Data and Learning Analytics in the field of education is shown. The main types of research questions for analyzing and improving educational technologies using Learning Analytics are highlighted. The principle of cumulative measurement is proposed for assessing the compliance condition, which determines the throughput of neural network algorithms and affects the success of training. The direction of using artificial intelligence in the formation of an adaptive learning environment designed for a specific individual, taking into account his cognitive characteristics, is highlighted. The possibility of using a neural network to analyze the emotional state of students and adjust the learning environment in accordance with this state is shown. By analogy with the simplified block diagram of neural network training, an adaptive learning model based on artificial intelligence technologies has been developed. With adaptive learning, taking into account the individual cognitive abilities of the student, the system processes the process of acquiring knowledge in the form of an analysis of his achievements, mistakes, physical, emotional state and other parameters. As a result of the collected and summarized information, a program adapted to the student is finalized, while constant self-learning and improvement of the system itself occurs. The relevance and prospects for the further implementation of neural networks in the educational process in general and in teacher education in particular are substantiated, allowing for an individual learning trajectory in each subject for each student, taking into account his capabilities and abilities.

1. Gulboev N.A., Duseinov N.E., Akhmedov B.A., Rakhmanova G.S. Models of electric grid manage-ment systems. Molodoi uchenyi. Tekhnicheskie nauki. Uzbekistan. 2020;22(312):105–107. EDN: KHYCYR. (In Russ.).

2. Yakubov M.S., Akhmedov B.A., Duseinov N.E., Abduraimov Zh.G. Analysis and new trends in the use of neural networks and arti-ficial intelligence in the modern higher educa-tion system. Ekonomika i sotsium. 2021;5–2(84):1148–1162. EDN: SHXNRV. (In Russ.).

3. Data Mining: Everything businesses and future professionals need to know about data mining. – URL: https://lpgenerator.ru/blog/chto-takoe-data-mining/?ysclid=loo4vpx3qe952428767 (date of application: 07.11.2023).

4. Arroway P., Morgan G., O’Keefe M., Yanosky R. Learning analytics in higher education. Jour-nal of Data Analysis and Information Pro-cessing 2016;3:148–155.

5. Dyckhoff A. Implications for learning analyt-ics tools. Meta-analysis of applied research questions. 2011: 594–601

6. Butorina T.S., Shirshov E.V., Ivanchenko A.A. Theory and practice of using neural technologies in the educational process of the university. Lesnoi zhurnal. 2004;2:80–85. (In Russ.).

7. Gidlevskii A.V. Theoretical and methodological foun-dations of the intellectual model of education. Intelli-gence. In: Culture. Education: materials of the All-Russian Scientific Jubilee. conf., dedicated. The 75th anniversary of his birth. acad. RAO I.S. Ladenko. No-vosibirsk, September 16-18. ‒ Novosibirsk. 2008:59‒60. (In Russ.).

8. Polishchuk V.R. How substances are investi-gated. Moscow:Nauka. Gl. red. fiz.-mat. litera-tury. 1989:224. (In Russ.).

9. Komenskii Ya.A. Selected pedagogical works. in 2 vol. vol.1. Moscow: Pedagogika. 1982:656. (In Russ.).

10. Ryabtseva I.V. The idea of pre-professional training and specialized education in the his-tory of pedagogical science. Sibirskii pedagog-icheskii zhurnal. 2003;3:217–225. EDN: NYGUFV. (In Russ.).

11. Kuzin A.Yu., Slavutskaya E.V., Slavutskii L.A. Deterministic neural network algorithm for processing psychodiagnostic data. Vestnik Chuvashskogo universiteta. 2011;3:137–141. EDN: ODAMMX. (In Russ.).

12. Khabibullin I.R., Azovtseva O.V., Gareev A.D. The relevance of using neural networks for educational purposes. Molodoi uchenyi. 2023;13(460):176–178. EDN: MCQBNQ. (In Russ.).

13. Nur Alia Syahirah Badrulhisham, Nur Nabilah Abu Mangshor. Emotion Recognition Using Convolutional Neural Network (CNN). In: Journal of Physics: Conference Series. The 1st International Conference on Engineering and Technology (ICoEngTech) 2021 15-16 March 2021. Perlis, Malaysia. 2021;1962:012040. http://doi.org/10.1088/1742-6596/1962/1/012040

14. Filatova O.N., Bulaeva M.N., Gushchin A.V. The use of neural networks in professional education. Problemy sovremennogo pedagog-icheskogo obrazovaniya. 2022;2:243–245. EDN: PHOBYS. (In Russ.).

15. Akhmedov B.A. The tasks of ensuring the reliability of cluster systems in a continuous educational envi-ronment. Eurasian Education Science and Innovation Journal. 2021;1(22):15–19. (In Russ.).

16. Starovoit A.N., Cherpakova N.A. The use of neural networks in educational institutions to improve the quality of education. Informatsiya i obrazovanie: granitsy kommunikatsii. 2023;15:169–170. (In Russ.).

17. Mukhamediev R., Popova Y., Kuchin Y., Zaitseva E., Kalimoldayev A. and oth. Review of Artificial Intelligence and Machine Learn-ing Technologies: Classification, Restrictions, Opportunities and Challenges. Mathematics. 2022;10(15):2552. https://doi.org/10.3390/math10152552

18. Saenko E.S. The use of multimedia tools and technologies to increase the motivation of students in teaching foreign languages. Dialog yazykov I kultur v sovremennom obrazovany-telnom prostranstve. 2022:59–61. (In Russ.).

19. Vai Yan.M. The use of neural networks to control and predict the results of the educational process at the university. In: The Fourth Cartesian readings "Rationalism and the universals of culture". Materials of the international scientific and practical conference. Moscow-Zelenograd. 2017;2:213–218. EDN: NRYSSJ. (In Russ.).

20. Mazurok T.L. A synergetic model of individu-alized learning management. Matematicheskie mashiny i sistemy. 2010;3:124–134. (In Russ.).