Back to timeline

Research · February 2015

Batch normalisation

Ioffe and Szegedy proposed normalising each layer's inputs by the statistics of the current batch, and training sped up several times over.

Why it matters

Deep networks began training predictably: careful initialisation and a tiny learning rate stopped being necessary.

The distribution of each layer's inputs shifts during training because the weights of earlier layers change, so every layer chases a moving target. Normalisation fixes the scale. The effect was strong enough that the method entered practically every architecture. Why exactly it works is still debated; the authors' original hypothesis was later disputed.

Event record

Event date
February 2015
Timeline date
Event date
Verification
Sources gathered automatically · September 17, 2026
Lines
ID
evt-0229

Preprint of 11 February 2015; presented at ICML 2015.

Sources

Related events