# Reconciling multiple simultaneous predictions with temporal pooling

**URL:** <https://discourse.numenta.org/t/reconciling-multiple-simultaneous-predictions-with-temporal-pooling/1654>\
**Category:** Numenta Theory\
**Tags:** prediction, temporal-pooling\
**Created:** [December 7, 2016, 2:24am UTC](https://discourse.numenta.org/t/reconciling-multiple-simultaneous-predictions-with-temporal-pooling/1654 "2016-12-07T02:24:09Z")\
**Posts on this page:** 1\
**Showing post:** 5

<div class="post-metadata">

**Author:** ![sunguralikaan](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/sunguralikaan/32/585_2.png) [@sunguralikaan](https://discourse.numenta.org/u/sunguralikaan)\
**Post date:** [December 9, 2016, 7:15am UTC](https://discourse.numenta.org/t/reconciling-multiple-simultaneous-predictions-with-temporal-pooling/1654/5 "2016-12-09T07:15:21Z")

</div>

> [@jakebruce](#):
>
> As it stands, the mechanism of “well-predicted cells activate slow currents in their postsynaptic targets” does exhibit the behavior of pooling across predictable boundaries even when those boundaries can branch.

1- This current decays in time, so recency has a factor here. Any particular activation is biased according to recent inputs.  
2- To my understanding it should not be about how many branches there are but how many frequent/significant ones there are. If there was few AC and lots of AB I do not see same columns representing both as a problem on the short term. On the opposite, maybe it should start like that.

> [@jakebruce](#):
>
> Basically what’s to stop AB from having the same representation as AC, since the A representation will persist through both AB and AC due to the slow persistent currents.

What stops same columns representing A and B and C in the default Spatial Pooler? They get represented differently because there are mechanisms creating competitions among columns such as synapse adaptation, boosting, bumping synapse permanences based on activation frequency.

The most recent temporal pooling implementation that is published on Nupic is an extension of Spatial Pooling. So there is a competition among columns just as SP. If AB and AC appears distinctively enough some columns will specialize on the total overlap of A+B and some will specialize on A+C.

[Pseudo-Pseudo Code](https://github.com/numenta/nupic.research/wiki/Union-Pooler-Psuedocode4)  
[Published Implementation](https://github.com/numenta/nupic.research/blob/86f6d2fe900c8f71becdc451156f16c4103a160c/htmresearch/algorithms/union_temporal_pooler.py)

Reservoir is just something I use not an official analogy but there were topics discussing temporal pooling implementations in the forums if you missed them. [1](https://discourse.numenta.org/t/new-tp-pseudocode/1603), [2](https://discourse.numenta.org/t/multistep-predictions-vs-predictions-from-predictions/1635)

Maybe these would help clear things up a bit if I am not making sense.

---

_[View the full topic](https://discourse.numenta.org/t/reconciling-multiple-simultaneous-predictions-with-temporal-pooling/1654)._