Usporedite metode

	Klasifikacija slika pomoću CNN-a	Slučajna šuma	Stroj potpornih vektora (klasifikacija)
Područje	Duboko učenje	Strojno učenje	Strojno učenje
Obitelj	Machine learning	Machine learning	Machine learning
Godina nastanka	2016	2001	1995
Tvorac	He, K. et al. (ResNet); Tan, M. & Le, Q.V. (EfficientNet)	Breiman, L.	Cortes, C. & Vapnik, V.
Vrsta	Deep convolutional neural network (supervised)	Ensemble (bagging of decision trees)	Maximum-margin classifier (kernel method)
Temeljni izvor	He, K., Zhang, X., Ren, S. & Sun, J. (2016). Deep Residual Learning for Image Recognition. CVPR.	Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32.	Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297.
Drugi nazivi	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	Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier
Srodne	5	4	5
Sažetak	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.	The Support Vector Machine, introduced by Corinna Cortes and Vladimir Vapnik in 1995, is a classifier that finds the optimal separating hyperplane between classes in a high-dimensional space. It chooses the boundary that leaves the widest possible margin to the nearest training points, which makes its decisions robust on new data.