# Dropout for the recurrent signal on LSTM units

**URL:** <https://discourse.julialang.org/t/dropout-for-the-recurrent-signal-on-lstm-units/73335>\
**Category:** Machine Learning\
**Tags:** flux\
**Created:** [December 19, 2021, 4:16pm UTC](https://discourse.julialang.org/t/dropout-for-the-recurrent-signal-on-lstm-units/73335 "2021-12-19T16:16:46Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Maxim\_Lubov](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/maxim_lubov/32/29744_2.png) [@Maxim\_Lubov](https://discourse.julialang.org/u/Maxim_Lubov)\
**Post date:** [December 19, 2021, 4:16pm UTC](https://discourse.julialang.org/t/dropout-for-the-recurrent-signal-on-lstm-units/73335/1 "2021-12-19T16:16:46Z")

</div>

Is there a possibility in Flux to apply dropout procedure to the recurrent input signal on the LSTM units, like `recurrent_dropout` in Keras?

---

<div class="post-metadata">

**Author:** ![ToucheSir](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/touchesir/32/14411_2.png) [@ToucheSir](https://discourse.julialang.org/u/ToucheSir)\
**Post date:** [December 20, 2021, 4:26pm UTC](https://discourse.julialang.org/t/dropout-for-the-recurrent-signal-on-lstm-units/73335/2 "2021-12-20T16:26:40Z")

</div>

Not at present, so a PR would be very welcome 🙂