YUQORI O'LCHAMLI MA'LUMOTLARDA MODEL MURAKKABLIGI VA BASHORAT ANIQLIGI O'RTASIDAGI MUVOZANAT: SUN'IY INTELLEKT NUQTAYI NAZARIDAN NAZARIY TAHLIL
Vol. 5 No. 17 (2026): Pedagogy and Psychology in the Modern World 32-36
Abstract
Mazkur maqolada yuqori o‘lchamli ma’lumotlarni tahlil qilishda sun’iy intellekt modellarining murakkabligi va bashorat aniqligi o‘rtasidagi nazariy muvozanat masalasi tahlil qilinadi. Tadqiqotda model parametrlarining ko‘payishi, ma’lumotlarning o‘lchamliligi, ortiqcha moslashuv, umumlashtirish qobiliyati va bashorat xatosi o‘rtasidagi o‘zaro bog‘liqlik tizimlashtiriladi. Klassik bias–variance trade-off konsepsiyasi zamonaviy overparameterized AI modellarining xususiyatlari bilan qiyosiy tahlil qilinib, model murakkabligining ortishi har doim ham umumlashtirish qobiliyatining pasayishiga olib kelmasligi asoslanadi. Shuningdek, regularizatsiya, o‘lchamni kamaytirish va model tanlash mexanizmlarining murakkablikni boshqarishdagi roli ochib beriladi. Natijada yuqori o‘lchamli muhitda model murakkabligi va bashorat aniqligi o‘rtasidagi optimal nisbatni belgilashga qaratilgan nazariy-metodologik yondashuv shakllantiriladi.
Keywords:
References
Belkin M., Hsu D., Ma S., Mandal S.** Reconciling Modern Machine-Learning Practice and the Classical Bias-Variance Trade-Off // Proceedings of the National Academy of Sciences. — 2019. — Vol. 116, No. 32. — P. 15849–15854.
Nakkiran P., Kaplun G., Bansal Y., Yang T., Barak B., Sutskever I.** Deep Double Descent: Where Bigger Models and More Data Hurt // Journal of Statistical Mechanics: Theory and Experiment. — 2021. — 124005.
D’Ascoli S., Refinetti M., Biroli G., Krzakala F.** Double Trouble in Double Descent: Bias and Variance(s) in the Lazy Regime // Proceedings of the 37th International Conference on Machine Learning. — 2020. — Vol. 119. — P. 2280–2290.
Fan J., Li R. Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties // Journal of the American Statistical Association. — 2001. — Vol. 96, No. 456. — P. 1348–1360.
Bühlmann P. Statistical Significance in High-Dimensional Linear Models // Bernoulli. — 2013. — Vol. 19, No. 4. — P. 1212–1242.
Nalsnick E., Smyth P., Tran D. A Brief Tour of Deep Learning from a Statistical Perspective // Annual Review of Statistics and Its Application. — 2023. — Vol. 10. — P. 219–246. — DOI: 10.1146/annurev-statistics-032921-013738.
Qizi, Jalilova Dilshoda Ural, Joʻraboyeva Malika, Jumayeva Muhlisa, and Jamolova Sevinch. "BOSHLANG ‘ICH SINFLAR ELEKTRON TAʼLIMDA MULTIMEDIANING O ‘RNI." Science and innovation 3, no. Special Issue 22 (2024): 206-207.
Qizi, Jalilova Dilshoda Ural, Poyonova Qandiya, Abdimurodova Maftuna, and Nahalboyeva Iroda. "UCHINCHI RENESSANS SHAROITIDA PEDAGOGIK TA’LIM SOHASIDA RAQAMLI TEXNOLOGIYALAR." Science and innovation 3, no. Special Issue 18 (2024): 637-640.
Wikle C.K., Zammit-Mangion A. Statistical Deep Learning for Spatial and Spatiotemporal Data // Annual Review of Statistics and Its Application. — 2023. — Vol. 10. — P. 247–270. — DOI: 10.1146/annurev-statistics-033021-112628.
Statistical Inference: Theoretical Development to Data Analytics // Handbook of Statistics. — 2020. — Vol. 43. — P. 289–335. — DOI: 10.1016/bs.host.2020.02.003.
Readership
Downloads
Published
Issue
Section
How to Cite
