Prehistory — From Neural Networks to the TransformerSergey Ioffe, Christian Szegedy (Google)Google

Google publishes Batch Normalization on arXiv

Batch Normalization released on arXiv

Why it matters

Stabilized and sped up the training of deep networks and was adopted as standard in most architectures

Source — Primary sources first; secondary reports are labelled “Press”

Paperarxiv.orghttps://arxiv.org/abs/1502.03167

Added in Week 35, 2026 · See that week

Nearby on the same axis

Human-level control through deep reinforcement learningPaperGoogle publishes Distilling the Knowledge in a Neural Network on arXivPaperAdam: A Method for Stochastic OptimizationPaperRonneberger, Fischer and Brox publish U-Net on arXivPaper