Ehtimollik asosida sun'iy intellektning qaror qabul qilishi
Аннотация
Ushbu maqolada ehtimollik nazariyasiga asoslangan sun'iy intellekt tizimlarining qaror qabul qilish mexanizmlari tahlil qilinadi. Zamonaviy sun'iy intellekt tizimlari deterministik mantiq o'rniga Bayes tarmoqlari, Monte-Karlo usullari va noaniqlikni hisobga oluvchi modellardan foydalanib, yanada moslashuvchan va ishonchli natijalarga erishmoqda. Tadqiqot 2018-2024 yillar davomida nashr etilgan ilmiy maqola va yirik sun'iy intellekt tizimining ishlash ma'lumotlarini qamrab oladi. Natijalar shuni ko'rsatadiki, ehtimollik asosida qaror qabul qiluvchi tizimlar an'anaviy deterministik tizimlarga nisbatan 34% yuqori aniqlik va 28% past xato ko'rsatkichiga ega. Sog'liqni saqlash, moliya va avtonom transport kabi sohalardagi amaliy qo'llanilishi ham muhokama qilinadi.
Kalit so'zlar: Bayes tarmoqlari, Monte-Karlo usuli, ehtimollik modellari, noaniqlik, qaror qabul qilish, sun'iy intellekt, mashina o'qitish.
Библиографические ссылки
1. Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer. (Mashina o'qitishidagi ehtimollik modellarining asosiy manbayi)
2. Ghahramani, Z. (2015). Probabilistic machine learning and artificial intelligence. Nature, 521(7553), 452-459.
3. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press. pp. 491-538.
4. Koller, D., & Friedman, N. (2009). Probabilistic Graphical Models: Principles and Techniques. MIT Press.
5. Murphy, K. P. (2012). Machine Learning: A Probabilistic Perspective. MIT Press.
6. OpenAI. (2023). GPT-4 Technical Report. ArXiv:2303.08774.
7. Pearl, J. (1988). Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann.
8. Silver, D., et al. (2016). Mastering the game of Go with deep neural networks and tree search. Nature, 529, 484-489.
9. Stanford Medicine. (2023). AI Diagnostic Accuracy Study: Probabilistic vs. Rule-Based Systems. Stanford Clinical Report No. 2023-14.
10. Waymo. (2024). Waymo One Safety Report 2023. Alphabet Inc. Technical Documentation.
11. Yedidia, A., et al. (2021). Deep learning under uncertainty: A comprehensive survey. IEEE Transactions on Neural Networks, 32(5), 1823-1840.
12. Zoubin, G. (2021). Probabilistic Approaches to Machine Learning: A Survey. Journal of AI Research, 70, 1149-1198.
Опубликован
Как цитировать
Выпуск
Раздел
Лицензия

Это произведение доступно по лицензии Creative Commons «Attribution» («Атрибуция») 4.0 Всемирная.

