Normalization methods

英文原文文件：normalization.md

计算解释

保障训练稳定性的方法，使优化过程适应深度、批次规模与分布式硬件约束。

支撑阅读卡

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (2015, single_gpu_deep_learning)
• Identity Mappings in Deep Residual Networks (2016, multi_gpu_dense_training)
• Layer Normalization (2016, multi_gpu_dense_training)
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour (2017, multi_gpu_dense_training)
• Group Normalization (2018, multi_gpu_dense_training)
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour with Batch Normalization (2018, multi_gpu_dense_training)

后续计算范式下过时或退居次要的内容

仅通过已链接的阅读卡追踪，不将本方法页视为独立证据来源。