TASVIRLARNI TASNIFLASHDA DENSENET169 YONDASHUVI: SAMARADORLIK VA QIYOSIY TAHLIL

Authors

  • Jaxongir Jalilov Muhammad al-Xorazmiy nomidagi Toshkent Axborot Texnologiyalari Universiteti, Sun’iy Intellekt fakulteti

Keywords:

Sun’iy intellekt, ResNet, Zich bog’langan tarmoq, CNN, InceptionNet.

Abstract

Sun’iy intellekt sohasida chuqur o‘rganish usullari keyingi o‘n yil ichida juda tez rivojlandi. Ayniqsa, kompyuter tasavvuri yo‘nalishida tasvirlarni avtomatik tasniflash muammosi uzoq yillardan beri tadqiqotchilarning e’tiborini tortib kelmoqda. Ilk davrlarda bu muammo ko‘p jihatdan qo‘lda tuzilgan belgilar va klassik statistik usullar yordamida hal etilardi. Ammo neyron tarmoqlar, xususan konvolyutsion neyron tarmoqlar (CNN) paydo bo‘lgandan so‘ng, tasniflash sifati tubdan o‘zgardi. Bugungi kunda ResNet, VGG, InceptionNet va DenseNet kabi arxitekturalar tasvirlarni tasniflash sohasida keng qo‘llanilmoqda. Ushbu maqolada ana shunday arxitekturalardan biri — DenseNet169 — uning tuzilishi, ishlash tamoyili, samaradorligi va boshqa modellar bilan qiyosiy tahlili ko‘rib chiqiladi.

References

Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4700-4708).

He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).

Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.

Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2818-2826).

Rajpurkar, P., Irvin, J., Ball, R. L., Zhu, K., Yang, B., Mehta, H., ... & Lungren, M. P. (2017). Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv preprint arXiv:1711.05225.

Tan, M., & Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning (pp. 6105-6114). PMLR.

Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.

Chollet, F. (2021). Deep Learning with Python, Second Edition. Manning Publications.

Downloads

Published

2026-04-15