AI engineering glossary · Deep learning core
What is BN (batch normalisation)?
Batch normalisation (also called BatchNorm, BN): A layer that standardises each feature across the mini-batch to zero mean and unit variance, then rescales it with learnable parameters. It stabilises training, allows larger learning rates and acts as mild regularisation, but depends on batch statistics.
Batch normalisation: an example
For a mini-batch of 64, it computes the mean and variance of each channel over those 64 examples, then applies gamma*x_hat + beta.
Related terms
More Deep learning core terms
- Batch renormalisation
- Batch size
- bfloat16
- Bias term
- Bidirectional RNN
- Binary cross-entropy
- Bottleneck
- Catastrophic forgetting
Where you learn it
Batch normalisation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.