UNIVERSITET MA'LUMOTLAR EKOTIZIMIDA INTELLEKTUAL TAHLIL: HETEROGEN MANBALARNI BIRLASHTIRISHNING MATEMATIK MODELI VA LOKALIZATSIYALANGAN ARXITEKTURA
Keywords:
heterogen ma’lumotlar, sun’iy intellekt, HEMIS, oliy ta’lim, integratsiya operatori, mashinaviy o‘qitish, katta til modellari, ma’lumotlar suvereniteti.Abstract
Zamonaviy oliy ta’lim muassasalari (OTM) HEMIS, o‘qitishni boshqarish tizimlari (LMS), elektron hujjat aylanish platformalari hamda video- va audio-xizmatlar tarkibida bir-biridan format, tuzilish va semantik jihatdan tafovutlanuvchi ma’lumotlar oqimini hosil qiladi. Mazkur xilma-xillik an’anaviy hisobot vositalarining tahliliy quvvatini cheklab qo‘yadi. Ushbu tadqiqotda heterogen manbalarni formal tavsiflashga mo‘ljallangan uchlik bazasidagi matematik model, ETL prinsiplariga asoslangan integratsiya operatori va sun’iy intellekt algoritmlarini baholash mezonlari taqdim etilgan. To‘rt model qiyosida XGBoost eng yuqori F1 = 0,85 qiymatini qayd etgan. Shuningdek, O‘zbekiston huquqiy maydonidagi ma’lumotlar suvereniteti talablari hamda texnik omillar sababli xalqaro katta til modellaridan (LLM) bevosita foydalanishning to‘siqlari va lokal implementatsiya — mahalliy serverlardagi ochiq vaznli modellar, nozik sozlash hamda federativ o‘qitish — afzalliklari ko‘rib chiqilgan.
Downloads
References
1. O‘zbekiston Respublikasi Prezidentining 2020-yil 5-oktabrdagi PF-6079-son “Raqamli O‘zbekiston — 2030” strategiyasini tasdiqlash to‘g‘risidagi farmoni // Qonunchilik ma’lumotlari milliy bazasi, 06.10.2020.
2. O‘zbekiston Respublikasi Prezidentining 2019-yil 8-oktabrdagi PF-5847-son “O‘zbekiston Respublikasi oliy ta’lim tizimini 2030-yilgacha rivojlantirish konsepsiyasini tasdiqlash to‘g‘risida”gi farmoni.
3. HEMIS (Higher Education Management Information System) — O‘zbekiston Respublikasi Oliy ta’lim, fan va innovatsiyalar vazirligi tomonidan davlat oliy ta’lim muassasalariga joriy etilgan yagona axborot tizimi. Rasmiy portal: hemis.uz
4. Lenzerini M. Data Integration: A Theoretical Perspective // Proceedings of the 21st ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems (PODS ’02). — ACM, 2002. — P. 233–246.
5. Doan A., Halevy A., Ives Z. Principles of Data Integration. — Morgan Kaufmann, 2012. — 520 p.
6. Siemens G., Long P. Penetrating the Fog: Analytics in Learning and Education // EDUCAUSE Review. — 2011. — Vol. 46, No. 5. — P. 30–40.
7. Romero C., Ventura S. Educational data mining and learning analytics: An updated survey // WIREs Data Mining and Knowledge Discovery. — 2020. — Vol. 10, No. 3. — e1355.
8. Breiman L. Random Forests // Machine Learning. — 2001. — Vol. 45, No. 1. — P. 5–32.
9. Chen T., Guestrin C. XGBoost: A Scalable Tree Boosting System // Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ’16). — ACM, 2016. — P. 785–794.
10. LeCun Y., Bengio Y., Hinton G. Deep Learning // Nature. — 2015. — Vol. 521. — P. 436–444.
11. Brown T., Mann B., Ryder N. et al. Language Models are Few-Shot Learners // Advances in Neural Information Processing Systems (NeurIPS 2020). — 2020. — Vol. 33. — P. 1877–1901.
12. Bommasani R., Hudson D.A., Adeli E. et al. On the Opportunities and Risks of Foundation Models. — Stanford CRFM Technical Report, 2021. — arXiv:2108.07258.
13. Ji Z., Lee N., Frieske R. et al. Survey of Hallucination in Natural Language Generation // ACM Computing Surveys. — 2023. — Vol. 55, No. 12. — P. 1–38.
14. O‘zbekiston Respublikasining 2019-yil 2-iyuldagi O‘RQ-547-son “Shaxsga doir ma’lumotlar to‘g‘risida”gi qonuni.
15. General Data Protection Regulation (EU) 2016/679. — Official Journal of the European Union, L 119, 4.5.2016.
16. Ahuja K., Diddee H., Hada R. et al. MEGA: Multilingual Evaluation of Generative AI // Proceedings of EMNLP 2023. — Association for Computational Linguistics, 2023.
17. Touvron H., Lavril T., Izacard G. et al. LLaMA: Open and Efficient Foundation Language Models. — arXiv:2302.13971, 2023.
18. McMahan B., Moore E., Ramage D. et al. Communication-Efficient Learning of Deep Networks from Decentralized Data // AISTATS 2017. — PMLR, 2017. — Vol. 54. — P. 1273–1282.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
License Terms of our Journal
