24.4k citations · 24.6k across the 2 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2017★ 246 cited
Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models
Sergey Ioffe
Batch Normalization is quite effective at accelerating and improving the training of deep models. However, its effectiveness diminishes when the training minibatches are small, or…
cs.LG2015★ 24.4k cited
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe, Christian Szegedy
Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This…