# Dropout regularization

**URL:** <https://discourse.julialang.org/t/dropout-regularization/3154>\
**Category:** Machine Learning\
**Tags:** tensorflow\
**Created:** [April 10, 2017, 11:10pm UTC](https://discourse.julialang.org/t/dropout-regularization/3154 "2017-04-10T23:10:32Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![hpoit](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/hpoit/32/245_2.png) [@hpoit](https://discourse.julialang.org/u/hpoit)\
**Post date:** [April 10, 2017, 11:10pm UTC](https://discourse.julialang.org/t/dropout-regularization/3154/1 "2017-04-10T23:10:32Z")

</div>

Hi Jon @malmaud, is `nn.dropout(cell, Tensor(output_keep_prob))` only for multi-cell nn? If my LSTM has only one cell state, then is there a need for it?

---

<div class="post-metadata">

**Author:** ![hpoit](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/hpoit/32/245_2.png) [@hpoit](https://discourse.julialang.org/u/hpoit)\
**Post date:** [April 11, 2017, 11:39am UTC](https://discourse.julialang.org/t/dropout-regularization/3154/2 "2017-04-11T11:39:00Z")

</div>

Thanks @vchuravy, was in doubt about the category and tag business.