https://arolstar52-zhtest.hf.space/index.php?action=history&feed=atom&title=Dropout
Dropout - 版本历史
2026-07-11T22:53:57Z
在这个wiki上该页的修订历史
MediaWiki 1.43.9
https://arolstar52-zhtest.hf.space/index.php?title=Dropout&diff=3334876&oldid=prev
imported>InternetArchiveBot：补救1个来源，并将0个来源标记为失效。) #IABot (v2.0.9.5
2023-11-10T12:18:56Z
<p>补救1个来源，并将0个来源标记为失效。) #IABot (v2.0.9.5</p>
<p><b>新页面</b></p><div>{{other uses|輟學生|other=2022年網路劇集迷你劇集|subject = Google提出的一种正则化技术}}<br />
{{expert|time=2019-12-11T06:42:48+00:00}}<br />
'''Dropout'''是Google提出的一种[[正则化 (数学)|正则化]]技术<ref name="pat">{{cite patent |title=System and method for addressing overfitting in a neural network |url=https://patents.google.com/patent/US9406017B2/en }} {{Wayback|url=https://patents.google.com/patent/US9406017B2/en |date=20210725074646 }} {{Cite web |url=https://patents.google.com/patent/US9406017B2/en |title=存档副本 |access-date=2019-12-11 |archive-date=2021-07-25 |archive-url=https://web.archive.org/web/20210725074646/https://patents.google.com/patent/US9406017B2/en |dead-url=unfit }}</ref>，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[[训练集|训练数据]]上产生复杂的相互适应。<ref name="pat" />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）。<ref name="MyUser_Jmlr.org_July_26_2015c">{{cite web |url=http://jmlr.org/papers/v15/srivastava14a.html |title=Dropout: A Simple Way to Prevent Neural Networks from Overfitting |newspaper=Jmlr.org |date= |author= |accessdate=July 26, 2015 |archive-date=2019-12-05 |archive-url=https://web.archive.org/web/20191205130609/http://www.jmlr.org/papers/v15/srivastava14a.html |dead-url=no }}</ref><ref>{{cite arxiv|last=Warde-Farley|first=David|last2=Goodfellow|first2=Ian J.|last3=Courville|first3=Aaron|last4=Bengio|first4=Yoshua|date=2013-12-20|title=An empirical analysis of dropout in piecewise linear networks|eprint=1312.6197|class=stat.ML}}</ref>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。<ref name="MyUser_Arxiv.org_July_26_2015c">{{cite arXiv |eprint=1207.0580|title= Improving neural networks by preventing co-adaptation of feature detectors |last1= Hinton |first1=Geoffrey E. |last2=Srivastava |first2=Nitish |last3=Krizhevsky |first3=Alex |last4=Sutskever |first4=Ilya |last5= Salakhutdinov |first5=Ruslan R. |class=cs.NE |year=2012 }}</ref><br />
<br />
{{ANN-stub}}<br />
<br />
== 参考文献 ==<br />
{{Reflist}}<br />
<br />
[[Category:机器学习]]<br />
[[Category:人工神经网络]]</div>
imported>InternetArchiveBot