# Feedback synapses

**URL:** <https://discourse.numenta.org/t/feedback-synapses/7135>\
**Category:** Numenta Theory\
**Created:** [February 2, 2020, 7:31pm UTC](https://discourse.numenta.org/t/feedback-synapses/7135 "2020-02-02T19:31:08Z")\
**Posts on this page:** 5\
**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:** [February 2, 2020, 7:31pm UTC](https://discourse.numenta.org/t/feedback-synapses/7135/1 "2020-02-02T19:31:08Z")

</div>

I understand the Context synapses in TM , but my question is what about the FEEDBACK.

How do they work in TM ? Where the signal comes from ? how does it impact Learning and/or Prediction ? In what way ! What is the algorithm ?

![image](https://canada1.discourse-cdn.com/flex030/uploads/numenta/original/2X/1/1396525db295ae2d7b693aa5bea40e2862faf6c7.png)

---

<div class="post-metadata">

**Author:** ![rogert](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/rogert/32/1294_2.png) [@rogert](https://discourse.numenta.org/u/rogert)\
**Post date:** [February 2, 2020, 9:56pm UTC](https://discourse.numenta.org/t/feedback-synapses/7135/2 "2020-02-02T21:56:06Z")

</div>

Apical synapses were implemented in the [ApicalTiebreakTemporalMemory algorithm](https://github.com/numenta/htmresearch/blob/master/htmresearch/algorithms/apical_tiebreak_temporal_memory.py) in htmresearch, which was used in the project described in the [Columns paper](https://github.com/numenta/htmpapers/tree/master/frontiers/a_theory_of_how_columns_in_the_neocortex_enable_learning_the_structure_of_the_world) (2017). The “output layer” in the paper is implemented by the [ColumnPooler algorithm](https://github.com/numenta/htmresearch/blob/master/htmresearch/algorithms/column_pooler.py) and its activity provides the apical “feedback” signal.

I don’t know whether apical feedback is used in more recent numenta work.

---

<div class="post-metadata">

**Author:** ![sheiser1](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/sheiser1/32/766_2.png) [@sheiser1](https://discourse.numenta.org/u/sheiser1)\
**Post date:** [February 2, 2020, 11:11pm UTC](https://discourse.numenta.org/t/feedback-synapses/7135/3 "2020-02-02T23:11:05Z")

</div>

> [@mraptor](#):
>
> How do they work in TM ? Where the signal comes from ? how does it impact Learning and/or Prediction ?

As I understand apical segments act like distal segments in a standard TM, in that they depolarize cells (make them predictive) but don’t activate them. The main difference is that the pre-synaptic cells on apical segments come from other TM regions. I’d recommend checking out the ApicalTiebreak algorithm in htmresearch as @rogert suggested.

---

<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:** [February 2, 2020, 11:25pm UTC](https://discourse.numenta.org/t/feedback-synapses/7135/4 "2020-02-02T23:25:33Z")

</div>

how do you decide when you have both Ctx and Feedback active ?  
When you only have the Ctx in a sense the neuron with the “highest” overlap wins !

But if you have Ctx and Fback active do the sum of overlap, avg of overlap or some other measure/algorithm is used to figure out which one wins ?

---

<div class="post-metadata">

**Author:** ![sheiser1](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/sheiser1/32/766_2.png) [@sheiser1](https://discourse.numenta.org/u/sheiser1)\
**Post date:** [February 3, 2020, 3:15am UTC](https://discourse.numenta.org/t/feedback-synapses/7135/5 "2020-02-03T03:15:42Z")

</div>

If there are 2 neurons in the same column both in the predictive state and that column then activates, both usually become winners and activate – inhibiting all other cells in that column. But if one of them has both distal _and_ apicals segment(s) active, that one becomes the lone winner. That’s the basic idea of the “Tiebreak” as I recall. Of course nothing beats checking the code tho! I think its commented pretty well.