11-laboratoriya ishi mavzu: Kuchaytirilgan o‘qitish (2 soat). Bajardi: Xayitov Alisher Laboratoriya ishining maqsadi va vazifalari

Topshiriqlar:
1. “Kuchaytirilgan o‘qitish”(Reinforcement Learning) mavzusida taqdimot tayyorlang.
2. “Domen bilimi”(Domain knowledge) mavzusida taqdimot tayyorlang.
3. “Muloqot qobiliyati”(Communication skill) mavzusida taqdimot tayyorlang.

Topshiriqni bajarish bo‘yicha ko‘rsatma:
Taqdimotni tayyorlash uchun MS PowerPoint, PowerPoint 365(OneDrive tarkibida) yoki Google Slides(Google drive)dan foydalanishingiz mumkin.


Hisobot shakli:
1. Laboratoriya ishining nomi.
2. Laboratoriya ishidagi topshiriq.
3. Topshiriqni bajarilishi
4. Topshiriq taqdimotini tayyorlash.
Nazorat savollari
1 Kuchaytirilgan o‘qitish (Reinforcement Learning)
2 Domen bilimi (Domain Knowledge)
3. Muloqot qobiliyati (Communication Skill)


Foydalanilgan adabiyotlar roʻyxati.
1. Section 0.1. Reading Mathematics, Vector Calculus, Linear Algebra, and Differential forms, 2009.
2. Aston Zhang, Zachary C. Lipton, MuLi, and Alexander J. Smola. Dive into DeepLearning Release 0.17.5. Mar 25, 2022. https://d2l.ai/d2l-en.pdf
3. François Chollet. Deep Learning with Python, Second Edition. October 2021 ISBN 9781617296864 504 pages. https://www.manning.com/books/deep-learning-with-pythonsecond-edition
4. Borovcnik, M. (2012). Multiple perspectives on the concept of conditional probability. Avances de Investigación en Educación Matemática, 2, 5–27. http://www.aiem.es/index.php/aiem/article/view/32.
5. Матвеев М.Г. Модели и методы искусственного интеллекта. Применение в экономике: учеб. пособие / М.Г. Матвеев, А.С. Свиридов, Н.А. Алейникова. — М.: Финансы и статистика; ИНФ РА-М, 2011. - 448 с.
6. Beazley, D.M. (2009). Python essential reference. Addison-Wesley Professional. Available at www.python.org (ac-cessed 18.03.2019).