Ioffe and Szegedy: batch normalization for deep-network training

What changed

Integrated trainable mini-batch normalization into deep networks, accelerating reported experiments.

Scientific scope

The record is the exact two-author ICML 2015 paper. Its internal-covariate-shift explanation, later theoretical reinterpretations, variants and claims that the method universally improves training remain separate.

Evidence

The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the exact two-author ICML 2015 paper. Its internal-covariate-shift explanation, later theoretical reinterpretations, variants and claims that the method universally improves training remain separate.

Contributors

• Sergey Ioffe · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Christian Szegedy · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.

• PMLR record for Batch Normalization
• PMLR full paper for Batch Normalization

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction