方法对比

	Dropout	批量归一化
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2014	2015
提出者	Srivastava, N.; Hinton, G.; Krizhevsky, A.; Sutskever, I.; Salakhutdinov, R.	Ioffe, S. & Szegedy, C.
类型	Stochastic regularization technique for neural networks	Normalization technique (applied per mini-batch during training)
开创性文献	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.	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.
别名	dropout regularization, stochastic dropout, neuron dropout, inverted dropout	BatchNorm, BN, batch norm, mini-batch normalization
相关	1	1
摘要	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.	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.