Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Basic Information
- Sergey Ioffe, Christian Szegedy from Google Reserch, @google.com
- 2015 ICML
Problem Description
在訓練Deep Neural Network的過程中,每層layer的input distribution都會隨著前一層的parameter而改變(Internal Covariate Shift),容易導致Model收斂緩不容易train,而Batch Normalization就是透過在每一層的input都做一次normalization,來解決Internal Covariates Shift,減緩Vanishing Gradient的問題,同時也達到regularization的效果。
About 13 min