# A recommended roadmap to implement Thousands Brains Theory?

**URL:** https://discourse.numenta.org/t/a-recommended-roadmap-to-implement-thousands-brains-theory/7876
**Category:** Engineering
**Created:** [September 17, 2020, 4:43am UTC](https://discourse.numenta.org/t/a-recommended-roadmap-to-implement-thousands-brains-theory/7876 "2020-09-17T04:43:43Z")
**Posts on this page:** 7
**Page:** 1

<div class="post-metadata">

### Author: ![marty1885](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/marty1885/32/1891_2.png) [@marty1885](https://discourse.numenta.org/u/marty1885)
#### Post date: [September 17, 2020, 4:43am UTC](https://discourse.numenta.org/t/a-recommended-roadmap-to-implement-thousands-brains-theory/7876/1 "2020-09-17T04:43:43Z")

</div>

Hi,

I’ve been trying to re-implement Thousands Brains Theory so people could experiment with it. But to no success.I still have no idea how TBT models cross cortial-column communications (and how exactly those works), how the displacement cells are emulated, etc…; after tens if not a hundred hours of reading related lectures and papers.

So far I’ve gone through

- All of Numenta’s papers
- [MIT RES.9-003 Brains, Minds and Machines Summer Course](https://www.youtube.com/watch?v=_svW8NV1A6k&list=PLUl4u3cNGP61RTZrT3MIAikp2G5EEvTjf)
- [Computational Cognitive Neuroscience, 2020](https://www.youtube.com/playlist?list=PLu02O8xRZn7xtNx03Rlq6xMRdYcQgEpar)
- [Computational Neuroscience](https://www.youtube.com/playlist?list=PLU51WLu1-VgAzgxChAZJYuZhiyQdd5V6z)

I think I’m missing some critical part. Any ideas?

---

<div class="post-metadata">

### Author: ![sheiser1](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/sheiser1/32/766_2.png) [@sheiser1](https://discourse.numenta.org/u/sheiser1)
#### Post date: [September 17, 2020, 6:04am UTC](https://discourse.numenta.org/t/a-recommended-roadmap-to-implement-thousands-brains-theory/7876/2 "2020-09-17T06:04:26Z")

</div>

Not sure how much this’ll help, but I’ve found it illuminating on how inter-layer and inter-column connections are enacted – through the Network API at least.

> **[numenta/htmresearch](https://github.com/numenta/htmresearch/tree/master/htmresearch/frameworks/layers)**
>
> Experimental algorithms. Unsupported. Contribute to numenta/htmresearch development by creating an account on GitHub.

---

<div class="post-metadata">

### Author: ![fcred](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/fcred/32/433_2.png) [@fcred](https://discourse.numenta.org/u/fcred)
#### Post date: [September 17, 2020, 8:12am UTC](https://discourse.numenta.org/t/a-recommended-roadmap-to-implement-thousands-brains-theory/7876/3 "2020-09-17T08:12:20Z")

</div>

Several [examples](https://github.com/htm-community/htm.core/tree/master/py/htm/advanced/examples) that test aspects of TBT have been ported from numenta/research to the htm.core implementation.

---

<div class="post-metadata">

### Author: ![marty1885](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/marty1885/32/1891_2.png) [@marty1885](https://discourse.numenta.org/u/marty1885)
#### Post date: [September 17, 2020, 9:38am UTC](https://discourse.numenta.org/t/a-recommended-roadmap-to-implement-thousands-brains-theory/7876/4 "2020-09-17T09:38:31Z")

</div>

Thank you! I’ll look into the code. It seems very clean and expressive. What material did you use to implement these?

---

<div class="post-metadata">

### Author: ![fcred](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/fcred/32/433_2.png) [@fcred](https://discourse.numenta.org/u/fcred)
#### Post date: [September 17, 2020, 9:57am UTC](https://discourse.numenta.org/t/a-recommended-roadmap-to-implement-thousands-brains-theory/7876/5 "2020-09-17T09:57:11Z")

</div>

Not my implementation. I just ported the code directly from numenta/research/projects.  
I don’t remember which projects specifically, but I choose the ones that had the most up to date TBT implementations. It shouldn’t be hard to find which projects as the examples use the same package names.

---

<div class="post-metadata">

### Author: ![Zbysekz](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/zbysekz/32/4299_2.png) [@Zbysekz](https://discourse.numenta.org/u/Zbysekz)
#### Post date: [September 22, 2020, 10:18am UTC](https://discourse.numenta.org/t/a-recommended-roadmap-to-implement-thousands-brains-theory/7876/6 "2020-09-22T10:18:12Z")

</div>

@marty1885 i am trying to use the code “thing classification” aka l2l4l6 experiment for 2D object recognition project + visualization with pandaVis. So far grid cells narrow union when object is recognised. Using just one macrocolumn, without lateral connections.  
These codes are using NetworkAPI, which is very nice.

If you would also use NAPI, you and people can use pandaVis, since it generates visualization automatically.

I will make some tutorial video about this, i am struggling to find time. But should be very soon.

---

<div class="post-metadata">

### Author: ![Zbysekz](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/zbysekz/32/4299_2.png) [@Zbysekz](https://discourse.numenta.org/u/Zbysekz)
#### Post date: [September 24, 2020, 10:49pm UTC](https://discourse.numenta.org/t/a-recommended-roadmap-to-implement-thousands-brains-theory/7876/7 "2020-09-24T22:49:55Z")

</div>

Here is the promised video tutorial:

> [@3D visualization tool - HTMpandaVis](https://discourse.numenta.org/t/3d-visualization-tool-htmpandavis/6707/21):
>
> Tutorial for HTMpandaVis: [[HTMpandaVis tutorial] ](https://www.youtube.com/watch?v=vBUx-75t11U)
