# Any ideas for an algorithm that learns directions?

**URL:** <https://discourse.numenta.org/t/any-ideas-for-an-algorithm-that-learns-directions/11745>\
**Category:** Engineering\
**Created:** [February 11, 2025, 10:16pm UTC](https://discourse.numenta.org/t/any-ideas-for-an-algorithm-that-learns-directions/11745 "2025-02-11T22:16:22Z")\
**Posts on this page:** 1\
**Showing post:** 13

<div class="post-metadata">

**Author:** ![Bitking](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/bitking/32/3099_2.png) [@Bitking](https://discourse.numenta.org/u/Bitking)\
**Post date:** [February 21, 2025, 4:37pm UTC](https://discourse.numenta.org/t/any-ideas-for-an-algorithm-that-learns-directions/11745/13 "2025-02-21T16:37:46Z")

</div>

As far as matching parts of image, one possible approach is to have multiple sized receptive fields at different levels or stages of processing. If there is no change on a “bigger” receptive field that feeds back to a lower level. The “edges” that get feedback that there is no change at the higher level but see a change at a lower level would indicate movement of a relatively larger object.

An “object” is a filled in space in the processing map at that level, composed of Calvin Tiles, as I have described many time in this forum. These roughly correspond to “grid cells.”

In the brain the spatial scaling in the various grid fields of the Entorhinal Cortex is about 1:1.14.

Please see this page for more details:  
[Number encoder based off of entoehinal grid cells - #2 by Bitking](https://discourse.numenta.org/t/number-encoder-based-off-of-entoehinal-grid-cells/3473/2)

The “new” vs. “old” that @cezar_t is mentioning can be the Alpha (10 Hz) basic processing rate in cortex. The relation between the fields can be both spatial (edge) and temporal (movement) pooling.

---

_[View the full topic](https://discourse.numenta.org/t/any-ideas-for-an-algorithm-that-learns-directions/11745)._