Dropout

Dropout是Google提出的一种正则化技术^[1]，用以在人工神经网络中对抗过拟合。Dropout有效的原因，是它能够避免在训练数据上产生复杂的相互适应。^[1]Dropout这个术语代指在神经网络中丢弃部分神经元（包括隐藏神经元和可见神经元）。^[2]^[3]在训练阶段，dropout使得每次只有部分网络结构得到更新，因而是一种高效的神经网络模型平均化的方法。^[4]

这是一篇与人工神经网络相关的小作品。你可以通过编辑或修订扩充其内容。

参考文献[编辑]

^ ^1.0 ^1.1 [1],“System and method for addressing overfitting in a neural network” （页面存档备份，存于互联网档案馆）存档副本. [2019-12-11]. 原始内容存档于2021-07-25.
^ Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Jmlr.org. [July 26, 2015]. （原始内容存档于2019-12-05）. 参数|newspaper=与模板{{cite web}}不匹配（建议改用{{cite news}}或|website=） (帮助)
^ Warde-Farley, David; Goodfellow, Ian J.; Courville, Aaron; Bengio, Yoshua. An empirical analysis of dropout in piecewise linear networks. 2013-12-20. arXiv:1312.6197  [stat.ML].
^ Hinton, Geoffrey E.; Srivastava, Nitish; Krizhevsky, Alex; Sutskever, Ilya; Salakhutdinov, Ruslan R. Improving neural networks by preventing co-adaptation of feature detectors. 2012. arXiv:1207.0580  [cs.NE].

[pat-1] 1.0 ^1.1 [1],“System and method for addressing overfitting in a neural network” （页面存档备份，存于互联网档案馆）存档副本. [2019-12-11]. 原始内容存档于2021-07-25.

[MyUser_Jmlr.org_July_26_2015c-2] Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Jmlr.org. [July 26, 2015]. （原始内容存档于2019-12-05）. 参数|newspaper=与模板{{cite web}}不匹配（建议改用{{cite news}}或|website=） (帮助)

[3] Warde-Farley, David; Goodfellow, Ian J.; Courville, Aaron; Bengio, Yoshua. An empirical analysis of dropout in piecewise linear networks. 2013-12-20. arXiv:1312.6197  [stat.ML].

[MyUser_Arxiv.org_July_26_2015c-4] Hinton, Geoffrey E.; Srivastava, Nitish; Krizhevsky, Alex; Sutskever, Ilya; Salakhutdinov, Ruslan R. Improving neural networks by preventing co-adaptation of feature detectors. 2012. arXiv:1207.0580  [cs.NE].

[1]

[2]

[3]

[4]