Prehistory — From Neural Networks to the TransformerGeoffrey Hinton et al. (University of Toronto)Geoffrey HintonUniversity of Toronto
Improving neural networks by preventing co-adaptation of feature detectors
Improving neural networks by preventing co-adaptation of feature detectors released on arXiv — proposed dropout
Why it matters
Curbed overfitting with simple regularization and later became a standard technique
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/1207.0580Added in Week 35, 2026 · See that week