Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

🤖 Plain-English Summary

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. Applied to a advanced image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.

🔑 Key Findings

• This slows down the training by requiring lower learning rates and careful parameter initialization, and makes it notoriously hard to train models with saturating nonlinearities.
• We refer to this phenomenon as internal covariate shift, and address the problem by normalizing layer inputs.
• Our method draws its strength from making normalization a part of the model architecture and performing the normalization for each training mini-batch.

🔗 Related Resources