Dropout

Dropout是ぜGoogle提出ていしゅつ的てき一いち种正せい则化技わざ术^[1]，用よう以在人工じんこう神しん经网络中ちゅう对抗过拟合あい。Dropout有效ゆうこう的てき原因げんいん，是ぜ它能够避免めん在ざい训练数すう据すえ上うえ产生复杂的てき相互そうご适应。^[1]Dropout这个术语代だい指ゆび在ざい神かみ经网络中丢弃部分ぶぶん神しん经元（包括ほうかつ隐藏神しん经元和わ可か见神经元）。^[2]^[3]在ざい训练阶段，dropout使し得とく每次まいじ只ただ有ゆう部分ぶぶん网络结构得え到いた更新こうしん，因いん而是一种高效的神经网络模型平均化的方法。^[4]

这是一いち篇へん与あずか人工じんこう神しん经网络相あい关的小しょう作品さくひん。您可以通过编辑或ある修おさむ订扩充其内容ないよう。

参考さんこう文献ぶんけん

^ ^1.0 ^1.1 [1],「System and method for addressing overfitting in a neural network」（页面存そん档备份，存そん于互联网档案あん馆）存そん档副本ふくほん. [2019-12-11]. 原始げんし内容ないよう存そん档于2021-07-25.
^ Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Jmlr.org. [July 26, 2015]. （原始げんし内容ないよう存そん档于2019-12-05）. 参さん数すう|newspaper=与あずか模も板ばん{{cite web}}不ふ匹ひき配はい（建けん议改用よう{{cite news}}或ある|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」（页面存そん档备份，存そん于互联网档案あん馆）存そん档副本ふくほん. [2019-12-11]. 原始げんし内容ないよう存そん档于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]. （原始げんし内容ないよう存そん档于2019-12-05）. 参さん数すう|newspaper=与あずか模も板ばん{{cite web}}不ふ匹ひき配はい（建けん议改用よう{{cite news}}或ある|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]