0PricingLogin
Deep Learning Academy · Lesson

Batch Norm & Layer Norm

Stabilize activations to train deeper.

Why Normalize Activations

As signals flow through layers, their scale drifts and training slows. Normalization keeps activations in a stable, well-behaved range. ⚖️

Batch Norm in One Line

Batch normalization rescales each feature using the mean and variance computed across the current mini-batch.

All lessons in this course

  1. Read the Train/Val Gap
  2. Dropout: Randomly Drop Neurons
  3. Batch Norm & Layer Norm
  4. Data Augmentation as Free Data
← Back to Deep Learning Academy