Neural Foundations · 2014
Dropout: A Simple Way to Prevent Neural Networks from Overfitting
Introduced dropout, a regularization method that randomly deactivates a fraction of units on each training pass, addressing the tendency of large neural networks to overfit by co-adapting their units to the training data.
Editorial record
Plain-language summary
During training, each unit is kept with some probability and dropped otherwise, so the network cannot rely on any specific combination of units and must learn features that are useful on their own. At test time all units are used with their outputs scaled to match, which approximates averaging over the many thinned networks seen during training. This reduced overfitting on a range of vision and speech tasks and became a standard technique for training large networks with limited data.
Source record
Provenance
- Record ID
- A-012
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.