Improving neural networks by preventing co-adaptation of feature detectors
Geoffrey E. Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, and Ruslan R. Salakhutdinov submitted the paper 'Improving neural networks by preventing co-adaptation of feature detectors' on July 3, 2012. The paper describes reducing overfitting by randomly omitting feature detectors during training and refers to the method as random dropout.
Historical classification
This verified record belongs to LINEAiGE's artificial-intelligence history layer beginning in 1956.
Why it matters
A documented research-publication milestone for dropout as a neural-network regularization technique.
People, organizations & technologies
PEOPLE
Geoffrey E. Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, Ruslan R. Salakhutdinov
TECHNOLOGIES
Dropout, Neural networks, Regularization
Evidence & verification
STATE
verified
CONFIDENCE
high
LAST VERIFIED
2026-09-11T17:05:13+08:00
The original arXiv record identifies the authors, July 3 2012 submission date, and the paper's dropout method. The later JMLR paper independently corroborates the method and authorship. The day-precision date is attached only to the arXiv submission milestone and is not asserted as the method's universal birth date. No geography, institutional affiliation, ancestry, influence, causality or relationships are inferred.
Sources
Improving neural networks by preventing co-adaptation of feature detectors
arXiv
PUBLISHED
2012-07-03
Dropout: A Simple Way to Prevent Neural Networks from Overfitting
Journal of Machine Learning Research
Dropout: A Simple Way to Prevent Neural Networks from Overfitting
University of Toronto
Trace the chronology
Record identity
LINEAiGE IDdropout-2012