Dropout (neural networks)

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search

Dropout is a regularization technique for reducing overfitting in neural networks by preventing complex co-adaptations on training data. It is a very efficient way of performing model averaging with neural networks.[1] The term "dropout" refers to dropping out units (both hidden and visible) in a neural network.[2]

See also[edit]


  1. ^ Hinton, Geoffrey E.; Srivastava, Nitish; Krizhevsky, Alex; Sutskever, Ilya; Salakhutdinov, Ruslan R. (2012). "Improving neural networks by preventing co-adaptation of feature detectors". arXiv:1207.0580Freely accessible [cs.NE]. 
  2. ^ "Dropout: A Simple Way to Prevent Neural Networks from Overfitting". Jmlr.org. Retrieved July 26, 2015. 


  1. ^ Warley-Farde et al,1312.6197 An empirical analysis of dropout in piecewise linear networks,2014(https://arxiv.org/abs/1312.6197)