Dropout

Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is $p=0.5$). At test time, all units are present, but with weights scaled by $p$ (i.e. $w$ becomes $pw$). The idea is to prevent co-adaptation, where the neural network becomes too reliant on particular connections, as this could be symptomatic of overfitting. Intuitively, dropout can be thought of as creating an implicit ensemble of neural networks.

相关学科： Batch NormalizationData AugmentationReLUSoftmaxImputationLSTMDropConnectMonte Carlo DropoutWeight DecayImage Classification

学科讨论

暂无讨论内容，你可以

学科管理组

暂无学科课代表，你可以申请成为课代表

重要学者

Yoshua Bengio

429868 被引用，1063 篇论文

Geoffrey E. Hinton

345738 被引用，408 篇论文

Albert-László Barabási

214997 被引用，510 篇论文

Yann LeCun

175383 被引用，366 篇论文

Ilya Sutskever

165856 被引用，113 篇论文

Tien Yin Wong

164688 被引用，2182 篇论文

Nan M. Laird

157185 被引用，366 篇论文

Ross Girshick

150810 被引用，165 篇论文

Anil K. Jain

148144 被引用，1055 篇论文

Christopher D. Manning

123173 被引用，515 篇论文