// ⬡ Deep Learning Foundations
Batch Normalization
Normalizes activations across a batch to stabilize deep training.
批归一化 2015 Foundational core
IN PLAIN WORDS
Subtract the batch mean, divide by std per channel, then learn a scale and shift. Enables stable, faster training in CNNs.
Used in: ResNet and most CNNs
TIMELINE · prerequisites → this → what builds on it
01Original paper
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe, Christian Szegedy · 2015
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
Learn first
Then you can learn
Related:RMSNorm
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
04Where the course teaches it
On learning paths:Zero to Deep Learning
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
batchnorm)