covariate shift和batch normalization问题

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/qq_30362711/article/details/84583412

1.1

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

1.1.1

论文Improving predictive inference under covariate shift by weighting the log-likelihood function 由于对hessian 矩阵非奇异不解，未完成。

2.1  WeightNormalization: ASimpleReparameterization toAccelerateTrainingofDeepNeuralNetworks

2.1.2Neural learning in structured parameter spaces

2.1.2.1 An Introduction to Multivariate Statistical Analysis (3ed)书

2.1.2.1.1 更高深度的概率论书籍