手法を比較

	AlexNet	バッチ正規化	Dropout
分野	深層学習	深層学習	深層学習
系統	Machine learning	Machine learning	Machine learning
提唱年	2012	2015	2014
提唱者	Krizhevsky, A.; Sutskever, I.; Hinton, G. E.	Ioffe, S. & Szegedy, C.	Srivastava, N.; Hinton, G.; Krizhevsky, A.; Sutskever, I.; Salakhutdinov, R.
種類	Deep Convolutional Neural Network (CNN)	Normalization technique (applied per mini-batch during training)	Stochastic regularization technique for neural networks
原典	Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems, 25, 1097–1105. (Republished: Communications of the ACM, 60(6), 84–90, 2017.)	Ioffe, S. & Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Proceedings of the 32nd International Conference on Machine Learning (ICML), PMLR 37, 448–456.	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.
別名	AlexNet, Krizhevsky net, SuperVision CNN, ImageNet CNN 2012	BatchNorm, BN, batch norm, mini-batch normalization	dropout regularization, stochastic dropout, neuron dropout, inverted dropout
関連	3	1	1
概要	AlexNet is a deep convolutional neural network (CNN) introduced by Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton in 2012. It won the ImageNet Large Scale Visual Recognition Challenge (ILSVRC 2012) with a top-5 error rate of 15.3%, outstripping the runner-up by more than 10 percentage points and reigniting broad interest in deep learning. The architecture introduced or popularised several techniques — ReLU activations, dropout regularisation, and multi-GPU training — that became standard practice across the field.	Batch Normalization is a training technique introduced by Sergey Ioffe and Christian Szegedy in 2015 that normalizes the pre-activation outputs of each layer using the mean and variance computed over the current mini-batch. By stabilizing the input distribution to each layer throughout training, it substantially reduces internal covariate shift, enabling the use of higher learning rates and making deep networks train faster and more reliably.	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.