Prehistory — From Neural Networks to the TransformerKaren Simonyan, Andrew Zisserman (University of Oxford)University of Oxford

Very Deep Convolutional Networks for Large-Scale Image Recognition (VGG)

Very Deep Convolutional Networks for Large-Scale Image Recognition (VGG) released on arXiv

Why it matters

Standardized the design of stacking small 3x3 convolutions deep

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

Paperarxiv.orghttps://arxiv.org/abs/1409.1556

Added in Week 35, 2026 · See that week

Same week

Neural Machine Translation by Jointly Learning to Align and TranslatePaper

Nearby on the same axis

Neural Machine Translation by Jointly Learning to Align and TranslatePaperGoogle publishes Sequence to Sequence Learning with Neural Networks on arXivPaperDeepMind publishes Neural Turing Machines on arXivPaperGoodfellow et al. publish Generative Adversarial Networks on arXivPaper