# TM-poolers synchronization/voting

**URL:** <https://discourse.numenta.org/t/tm-poolers-synchronization-voting/7491>\
**Category:** Numenta Theory\
**Created:** [May 1, 2020, 5:13pm UTC](https://discourse.numenta.org/t/tm-poolers-synchronization-voting/7491 "2020-05-01T17:13:18Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![mraptor](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/mraptor/32/4469_2.png) [@mraptor](https://discourse.numenta.org/u/mraptor)\
**Post date:** [May 1, 2020, 5:13pm UTC](https://discourse.numenta.org/t/tm-poolers-synchronization-voting/7491/1 "2020-05-01T17:13:18Z")

</div>

I haven’t seen discussion OR docs on how does the TPoolers vote/sync so that they generate single SDR/output

The straightforward solution seem to be simple UNION, but this if it works will work only for small numbers of TP’s

What would be a good target union-sparsity : 20% ?  
In my tests ~10 items fill ~20%, ~50 items fill ~65%, ~100 items fill ~85%

BTW: the same goes for the TP itself … this is the only thing I have :

> **[numenta/htmresearch](https://github.com/numenta/htmresearch/wiki/Overview-of-the-Temporal-Pooler)**
>
> Experimental algorithms. Unsupported. Contribute to numenta/htmresearch development by creating an account on GitHub.