# Relative Coordinate Encoder

**URL:** <https://discourse.numenta.org/t/relative-coordinate-encoder/5873>\
**Category:** NuPIC\
**Tags:** encoders, question\
**Created:** [April 22, 2019, 1:53pm UTC](https://discourse.numenta.org/t/relative-coordinate-encoder/5873 "2019-04-22T13:53:11Z")\
**Posts on this page:** 1\
**Showing post:** 6

<div class="post-metadata">

**Author:** ![rhyolight](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/rhyolight/32/3922_2.png) [@rhyolight](https://discourse.numenta.org/u/rhyolight)\
**Post date:** [April 24, 2019, 3:05pm UTC](https://discourse.numenta.org/t/relative-coordinate-encoder/5873/6 "2019-04-24T15:05:27Z")

</div>

I would not say _deprecated_, but you have more options. There has been lots of work on this recently, check these out!

> [@Grid Cell Encoder](https://discourse.numenta.org/t/grid-cell-encoder/5796):
>
> Hi all, The community fork now includes an encoder which converts 2-D coordinates into plausible grid cell module activity: To generate pictures like this one, call: python3 -m nupic.encoders.grid\_cell\_encoder See also the help message: python3 -m nupic.encoders.grid\_cell\_encoder --help

> [@Grid Cell Inspired Scalar Encoder](https://discourse.numenta.org/t/grid-cell-inspired-scalar-encoder/4242):
>
> After several days of thinking about grid cells and localization (still trying to grok a plausible mechanism that would give rise to the observed grid cell behavior), I finally made a somewhat related connection back to the encoders that I thought I would run by the HTM community. While considering the 1D example of grid cell behavior in @rhyolight’s HTM School video, I came up with a simple scalar encoder that I believe has some rather nice properties and is also fairly simple to implement. Th…

> [@Path anomoly detection using Grid Cells and Temporal Memory](https://discourse.numenta.org/t/path-anomoly-detection-using-grid-cells-and-temporal-memory/5167):
>
> I’m surprised that no one has ever tried grid cells as location encoders (like to the old GeoSpatial Encoder) for anomaly detection. So it became an experiment I ran for the final project for my ML course. Here is a screen shot for your viewing pleasure. And letting me to explain things more clearly. On the left you see a white and red circle revolving in a circle. That is the target. HTM will try to learn lt’s path and generate anomaly signals when even the path is altered. On the …

---

_[View the full topic](https://discourse.numenta.org/t/relative-coordinate-encoder/5873)._