# Question about linking individual TMs

**URL:** <https://discourse.numenta.org/t/question-about-linking-individual-tms/7683>\
**Category:** Getting Started\
**Created:** [June 28, 2020, 10:18pm UTC](https://discourse.numenta.org/t/question-about-linking-individual-tms/7683 "2020-06-28T22:18:17Z")\
**Posts on this page:** 1\
**Showing post:** 24

<div class="post-metadata">

**Author:** ![Andrew\_Stephan](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/andrew_stephan/32/4553_2.png) [@Andrew\_Stephan](https://discourse.numenta.org/u/Andrew_Stephan)\
**Post date:** [July 29, 2020, 8:38pm UTC](https://discourse.numenta.org/t/question-about-linking-individual-tms/7683/24 "2020-07-29T20:38:07Z")

</div>

> [@thanh-binh.to](#):
>
> fusion of invariant texts with all possible image appearances

I did try something similar to that–combining the invariant scalar label encoding with the images. I haven’t done much testing on its ability to recognize new digits, since what I’m actually interested in is whether the system can take the scalar label and produce an image to match. Image generation rather than image recognition. (See my last post: [Input-invariant representations](https://discourse.numenta.org/t/input-invariant-representations/7761) )

---

_[View the full topic](https://discourse.numenta.org/t/question-about-linking-individual-tms/7683)._