# One confusion regarding dropout

**URL:** <https://discuss.pytorch.org/t/one-confusion-regarding-dropout/81813>\
**Category:** Uncategorized\
**Created:** [May 18, 2020, 12:50pm UTC](https://discuss.pytorch.org/t/one-confusion-regarding-dropout/81813 "2020-05-18T12:50:57Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\
**Post date:** [May 19, 2020, 9:03am UTC](https://discuss.pytorch.org/t/one-confusion-regarding-dropout/81813/2 "2020-05-19T09:03:48Z")

</div>

This technique is called DropConnect and is described in [this paper](http://yann.lecun.com/exdb/publis/pdf/wan-icml-13.pdf).  
An implementation is discussed [here](https://discuss.pytorch.org/t/dropconnect-implementation/70921).

I haven’t seen a wide adoption of this technique, but I cannot claim one is superior over the other.

---

_[View the full topic](https://discuss.pytorch.org/t/one-confusion-regarding-dropout/81813)._