# Spatial Pooler Implementation for MNIST Dataset

**URL:** <https://discourse.numenta.org/t/spatial-pooler-implementation-for-mnist-dataset/2317>\
**Category:** Implementations\
**Tags:** spatial-pooling, htm-implementations\
**Created:** [May 13, 2017, 4:23pm UTC](https://discourse.numenta.org/t/spatial-pooler-implementation-for-mnist-dataset/2317 "2017-05-13T16:23:22Z")\
**Posts on this page:** 1\
**Showing post:** 20

<div class="post-metadata">

**Author:** ![vpuente](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/vpuente/32/4115_2.png) [@vpuente](https://discourse.numenta.org/u/vpuente)\
**Post date:** [July 11, 2019, 9:30am UTC](https://discourse.numenta.org/t/spatial-pooler-implementation-for-mnist-dataset/2317/20 "2019-07-11T09:30:58Z")

</div>

Log boosting seems to create a lot of spurious synapses in TM. If i’m correct, when the activity of a mini-column is low, the boostOverlaps\_ of that mini-column is “huge”. That makes that the winners for the same input change substantially.

As a note of caution seems like homeostatic synaptic plasticity (the mechanism behind boost) is disabled in L4 quite soon (After the animal was born [1]). Most of the papers about homeostatic synaptic plasticity talk about the inverse proportion between activation frequency and mEPSC voltage [2] (which ultimately affects who will win the inhibition).

In any case, in [2] you can read:

> Currently, we know little about the cellular  
> and molecular mechanisms underlying homeostatic plasticity in vivo.

[1] A. Maffei, S. B. Nelson, and G. G. Turrigiano, “Selective reconfiguration of layer 4 visual cortical circuitry by visual deprivation,” _Nat. Neurosci._ , vol. 7, no. 12, pp. 1353–1359, 2004.

[2] G. Turrigiano, “Homeostatic synaptic plasticity: Local and global mechanisms for stabilizing neuronal function,” _Cold Spring Harb. Perspect. Biol._ , vol. 4, no. 1, pp. 1–17, 2012.

---

_[View the full topic](https://discourse.numenta.org/t/spatial-pooler-implementation-for-mnist-dataset/2317)._