SUN’IY INTELLEKT VA UNING ASOSIY TUSHUNCHALARI
Keywords:
sun’iy intellekt, mashinaviy o‘qitish, chuqur o‘rganish, neyron tarmoqlar, ekspert tizimlar, kompyuter ko‘rishi, tabiiy tilni qayta ishlash, avtomatlashtirish, katta ma’lumotlarAbstract
Ushbu maqola sun’iy intellektning mohiyati, rivojlanish bosqichlari, asosiy yo‘nalishlari va uning turli sohalardagi qo‘llanilish imkoniyatlarini chuqur ilmiy-uslubda yoritadi. Sun’iy intellekt tizimlari inson fikrlashi, tahlil qilish, o‘rganish va qaror qabul qilish kabi jarayonlarni kompyuterda modellashtiradi. Maqolada mashinaviy o‘qitish, chuqur o‘rganish, neyron tarmoqlar, tabiiy tilni qayta ishlash va kompyuter ko‘rishi kabi yo‘nalishlarning nazariy asoslari va amaliy ahamiyati keng yoritilgan. Shuningdek, sun’iy intellektning afzalliklari, cheklovlari, xavfsizlik masalalari va kelajakdagi rivojlanish tendensiyalari haqida ham fikr yuritiladi.
References
1. Jordan, J. Intro to optimization in deep learning: Gradient Descent/ J. Jordan // Paper-space.Series:Optimization.– 2018. – URL: https://blog.paperspace.com/intro-to-optimiza-tion-in deep-learning-gradient-descent/
2. Scikit-learn – машинное обучение на Python. – URL: http://scikit-learn.org/stable/ modules/generated/sklearn.neural_network. MLPClassifier.html
3. Keras documentation: optimizers. – URL: https://keras.io/optimizers
4. Ruder, S. An overview of gradient descent optimization algorithms / S. Ruder // Cornell University Library. – 2016. – URL: https://arxiv. org/abs/1609.04747
5. Robbins, H. A stochastic approximation method / H. Robbins, S. Monro // The annals of mathematical statistics. – 1951. – Vol. 22. – P. 400–407.
6. Kukar, M. Cost-Sensitive Learning with Neural Networks / M. Kukar, I. Kononenko // Machine Learning and Data Mining : proceed-ings of the 13th European Conference on Artifi cial Intelligence. – 1998. – P. 445–449.
7. Duchi, J. Adaptive Subgradient Methods for Online Learning and Stochastic Optimiza-tion / J. Duchi, E. Hazan, Y. Singer // The Jour-nal of Machine Learning Research. – 2011. – Vol. 12. – P. 2121–2159.
8. Zeiler, M. D. ADADELTA: An Adap-tive Learning Rate Method / Cornell Univer-sity Library. – 2012. – URL: https://arxiv.org/ abs/1212.5701
9. Kingma, D. P. Adam: A Method for Sto-chastic Optimization / D. P. Kingma, J. Ba // Cor nell University Library. – 2014. – URL: https:// arxiv.org/abs/1412.6980 10. Гудфеллоу, Я. Глубокое обучение / Я. Гу-дфеллоу, И. Бенджио, А. Курвилль. – М. : ДМК Пресс, 2018. – 652 с.
11. Fletcher, R. Practical methods of optimi-zation / R. Fletcher. – Wiley, 2000. – 450 p.
12. Schraudolph, N. N. A Stochastic Qua-si-Newton Method for Online Convex Optimiza-tion / N.N. Schraudolph, J. Yu, S. Gunter // Sta-tistical Machine Learning. –2017.–URL: http:// proceedings.mlr.press/v2/schraudolph07a/ schraudolph07a.pdf Uzbekistan www.scientificprogress.uz Page 106 SCIENTIFIC PROGRESS VOLUME 4 ǀ ISSUE 5 ǀ 2023 ISSN: 2181-1601 Scientific Journal ImpactFactor(SJIF2022=5.016)Passport:http://sjifactor.com/passport.php?id=2227
13. Ruder, S. Optimization for Deep Learn-ing Highlights in 2017 / S. Ruder // Optimization for Deep Learning Highlights in 2017. – 2017. – URL: http://ruder.io/deep-learning-optimiza tion-2017.
14. Рахимов, К. (2022). Тенденции развития анализа данных, искусственного интеллекта и интернета вещей. Gospodarka i Innowacje., 30, 209-211.
15. Ortiqovich, Q. R., & Mamurovich, V. R. (2022). Mashinali o’qitish matematik modellari tasnifi. o'zbekistonda fanlararo innovatsiyalar va ilmiy tadqiqotlar jurnali, 2(14), 804-811.
16. Raximov, Q., & Sotvoldiyev , A. D. o‘g‘li. (2023). Neyron tarmoqlarining yangi turlarini tahlil qilish. international scientific and practical conference "the time of scientific progress ", 2(4), 106–112. Retrieved from http://academicsresearch.ru/index.php/ispcttosp/article/view/1500
17. Ortiqovich, Q. R. (2022). Vorisli deformasiyalanuvchi konsruksiya-larninng flatter masalasi. o'zbekistonda fanlararo innovatsiyalar va ilmiy tadqiqotlar jurnali, 2(14), 812-817.
18. Tojimamatov, I. N., Mamalatipov, O. M., & Karimova, N. A. (2022). SUN’IY NEYRON TARMOQLARINI O ‘QITISH USULLARI. Oriental renaissance: Innovative, educational, natural and social sciences, 2(12), 191-203.
19. Tojimamatov, I. N., Mamalatipov, O., Rahmatjonov, M., & Farhodjonov, S. (2023). NEYRON TARMOQLAR. Наука и инновация, 1(1), 4-12.
20. Ne’matjonov, F. F., Jahongirova, J. J., Murodov, B. S., & Tojimamatov, I. N. (2023). CREATE DATA CUBE WITH MS EXCEL. European International Journal of Multidisciplinary Research and Management Studies, 3(03), 77-86.
21. Kimyonazarova, D., Ne'matjonova, D., Ergasheva, B., & Tojimamatov, I. (2023, March). KATTA MA’LUMOTLAR BILAN ISHLASHDA HADOOP ARXITEKTURASI. In Международная конференция академических наук (Vol.2, No. 3, pp. 96-99).
22. Onarqulov, M., Yaqubjonov, A., & Yusupov, M. (2022). Computer networks and learning from them opportunities to use. Models and methods in modern science, 1(13), 59-62.
23. Karimberdiyevich, O. M., Mahamadamin o'g'li, Y. A., & Abdulaziz o'g'li, Y. M. (2023). MASHINALI O'QITISH ALGORITMLARI ASOSIDA BASHORAT QILISH USULLARINI YARATISH. Journal of new century innovations, 22(2),165-167.
24. Mamirovich, I. S. (2022). Finlyandiya Va O ‘Zbekistonda Ta ‘Lim Tizimini Sifatini Solishtirma Taxlili. Miasto Przyszłości, 29, 347-350..
