So sánh phương pháp
Xem các phương pháp đã chọn cạnh nhau; những hàng khác biệt được làm nổi bật.
| Phân loại ảnh bằng CNN× | Rừng ngẫu nhiên× | XGBoost× | |
|---|---|---|---|
| Lĩnh vực≠ | Học sâu | Học máy | Học máy |
| Họ | Machine learning | Machine learning | Machine learning |
| Năm ra đời≠ | 2016 | 2001 | 2016 |
| Người khởi xướng≠ | He, K. et al. (ResNet); Tan, M. & Le, Q.V. (EfficientNet) | Breiman, L. | Chen, T. & Guestrin, C. |
| Loại≠ | Deep convolutional neural network (supervised) | Ensemble (bagging of decision trees) | Ensemble (gradient-boosted decision trees) |
| Công trình gốc≠ | He, K., Zhang, X., Ren, S. & Sun, J. (2016). Deep Residual Learning for Image Recognition. CVPR. DOI ↗ | Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32. DOI ↗ | Chen, T. & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD, 785–794. DOI ↗ |
| Tên gọi khác≠ | CNN — Görüntü Sınıflandırma (ResNet / VGG / EfficientNet), convolutional neural network image classifier, deep image classification, ResNet / VGG / EfficientNet | Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble | XGBoost, extreme gradient boosting, scalable tree boosting |
| Liên quan≠ | 5 | 4 | 5 |
| Tóm tắt≠ | CNN image classification uses deep convolutional architectures such as ResNet (He et al., 2016), VGG and EfficientNet (Tan & Le, 2019) to sort images into categories. Stacked convolutional layers learn a hierarchy of visual features directly from pixels, and skip (residual) connections prevent the vanishing-gradient problem in very deep networks. | Random Forest is an ensemble learning method, introduced by Leo Breiman in 2001, that grows many decision trees on bootstrap samples of the data and combines their votes to produce strong classification and regression. By pooling many slightly different trees, it produces more accurate and more stable predictions than any single tree. | XGBoost (Extreme Gradient Boosting) is a scalable tree-boosting algorithm introduced by Tianqi Chen and Carlos Guestrin in 2016. It builds a strong predictor by adding decision trees one at a time, each correcting the errors left by the trees before it, and is a powerful prediction method widely used in competitions. |
| ScholarGateBộ dữ liệu ↗ |
|
|
|