Võrdle meetodeid

	Väljalangemine	ResNet (Residual Network)
Valdkond	Süvaõpe	Süvaõpe
Perekond	Machine learning	Machine learning
Tekkeaasta	2014	2016
Looja	Srivastava, N.; Hinton, G.; Krizhevsky, A.; Sutskever, I.; Salakhutdinov, R.	He, K.; Zhang, X.; Ren, S.; Sun, J.
Tüüp	Stochastic regularization technique for neural networks	Deep Convolutional Neural Network with skip connections
Algallikas	Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research, 15, 1929–1958.	He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778.
Rööpnimetused	dropout regularization, stochastic dropout, neuron dropout, inverted dropout	ResNet, Residual Network, Deep Residual Learning, ResNet-50
Seotud	1	4
Kokkuvõte	Dropout is a stochastic regularization technique for training deep neural networks, introduced by Srivastava, Hinton, Krizhevsky, Sutskever, and Salakhutdinov in 2014. During each training step, each neuron is independently switched off with probability (1 − p), preventing the network from co-adapting its units too tightly and thereby reducing overfitting.	ResNet (Residual Network) is a deep convolutional neural network architecture introduced by Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun at CVPR 2016. By inserting shortcut (skip) connections that carry the input of a block directly to its output — defining the block's task as learning a residual correction rather than a full mapping — ResNet enabled training of networks with hundreds or even thousands of layers without the vanishing-gradient degradation that had previously made very deep networks impractical. It won the ILSVRC 2015 image recognition competition with a top-5 error of 3.57% and remains the most widely used backbone architecture in computer vision.