# Encoding vision for HTM

**URL:** <https://discourse.numenta.org/t/encoding-vision-for-htm/2780>\
**Category:** Numenta Theory\
**Tags:** encoders, vision\
**Created:** [September 5, 2017, 10:26pm UTC](https://discourse.numenta.org/t/encoding-vision-for-htm/2780 "2017-09-05T22:26:12Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![jakebruce](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/jakebruce/32/996_2.png) [@jakebruce](https://discourse.numenta.org/u/jakebruce)\
**Post date:** [September 5, 2017, 11:31pm UTC](https://discourse.numenta.org/t/encoding-vision-for-htm/2780/2 "2017-09-05T23:31:03Z")

</div>

> [@No influence of learning based on the permanence of proximal connections](https://discourse.numenta.org/t/no-influence-of-learning-based-on-the-permanence-of-proximal-connections/2757/32):
>
> do we apply inhibition to the neighboring pixels? If not, why not?

This would be worth trying, but I anticipate problems. If you had some feature map of scalars you were encoding in the input, then I can see how this would be useful, as a sort of non-maximal-suppression approach. If you’ve got edges, or +/- intensity events, then I’m not sure you’d want to do this, because it could wipe out pixels that do actually contain edges (or events).

---

_[View the full topic](https://discourse.numenta.org/t/encoding-vision-for-htm/2780)._