Year: 2026
Type: conference-paper
Abstract: Mazkur maqolada zamonaviy mashinali o‘qitish algoritmlarining nazariy asoslari, matematik modellari hamda amaliy qo‘llanilish imkoniyatlari tahlil qilingan. Tadqiqotda sun’iy intellekt modellarining optimallashtirish jarayonlari, yo‘qotish funksiyalari va gradient tushishi algoritmlarining ishlash prinsiplari ko‘rib chiqilgan. Shuningdek, klassik mashinaviy o‘rganish algoritmlaridan Random Forest, Support Vector Machine (SVM) hamda Gradient Boosting va XGBoost modellarining matematik asoslari, afzalliklari va cheklovlari tahlil etilgan. Ushbu algoritmlarning sensor signallarini qayta ishlash, texnik diagnostika, tasvirlarni klassifikatsiya qilish va material xossalarini bashoratlashdagi samaradorligi yoritilgan. Tadqiqot natijalari klassik mashinaviy o‘rganish algoritmlarining kichik va o‘rta hajmdagi ma’lumotlarda yuqori aniqlik bilan ishlashini ko‘rsatadi.
DOI: 10.65164/a3pfjr69
Authors: Primbetov Abbaz, Primbetov Aziz
Institution: Nukus State Technical University
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Keywords: machine learning algorithms, artificial intelligence models, optimization algorithms, loss functions, gradient-based learning, random forest, support vector machine, gradient boosting, XGBoost, sensor signal processing, technical diagnostics, image classification, materials property prediction
Open Access status: gold
OpenAlex ID: W7168287659
