Architectures · intermediate · concept 61 of 176
Normalization Layers (BatchNorm to RMSNorm)
Layers that rescale activations so training stays stable as networks get deep. BatchNorm made deep CNNs trainable, LayerNorm made transformers possible, and RMSNorm is the leaner variant inside most current LLMs. Unglamorous, and load-bearing for everything.
Key terms
Batch normalizationLayer normalizationRMSNormInternal covariate shiftTraining stability
Learn these first
Where you meet it in the real world
Every deep network trained since 2015; pre-norm vs post-norm is a real LLM design decision
Videos
▶ Why Does Batch Norm Work? (C2W3L06) ↗
DeepLearningAI · YouTube
▶ Group Normalization (Paper Explained) ↗
Yannic Kilcher · YouTube
Guides and articles
8.5. Batch Normalization — Dive into Deep Learning 1.0.3 documentation ↗
Dive into Deep Learning
Courses, papers, and more