# Spatial Pooler Question

**URL:** <https://discourse.numenta.org/t/spatial-pooler-question/2224>\
**Category:** NuPIC\
**Created:** [April 15, 2017, 2:17pm UTC](https://discourse.numenta.org/t/spatial-pooler-question/2224 "2017-04-15T14:17:18Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Vibin\_Roy](https://avatars.discourse-cdn.com/v4/letter/v/48db29/32.png) [@Vibin\_Roy](https://discourse.numenta.org/u/Vibin_Roy)\
**Post date:** [April 15, 2017, 2:17pm UTC](https://discourse.numenta.org/t/spatial-pooler-question/2224/1 "2017-04-15T14:17:18Z")

</div>

I’ve a question on the SP. If I run a sequence A,B,C through a SP, would it be fair to say that the activeColumns I get after sp.compute for C would include the learning of both A and B with learning = True? If yes, then would it be ok to say this output SDR represents the sequence ABC?

---

<div class="post-metadata">

**Author:** ![rhyolight](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/rhyolight/32/3922_2.png) [@rhyolight](https://discourse.numenta.org/u/rhyolight)\
**Post date:** [April 16, 2017, 3:03pm UTC](https://discourse.numenta.org/t/spatial-pooler-question/2224/2 "2017-04-16T15:03:36Z")

</div>

No, you are confusing spatial pooling with temporal memory. The SP does not do sequence memory. Have you seen all the [HTM School](http://numenta.org/htm-school/) videos?