# Related knowledge with HTM?

**URL:** <https://discourse.numenta.org/t/related-knowledge-with-htm/9733>\
**Category:** Related Papers\
**Tags:** question\
**Created:** [May 17, 2022, 1:29pm UTC](https://discourse.numenta.org/t/related-knowledge-with-htm/9733 "2022-05-17T13:29:17Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![q228503](https://avatars.discourse-cdn.com/v4/letter/q/e19b73/32.png) [@q228503](https://discourse.numenta.org/u/q228503)\
**Post date:** [May 17, 2022, 1:29pm UTC](https://discourse.numenta.org/t/related-knowledge-with-htm/9733/1 "2022-05-17T13:29:17Z")

</div>

Hi,

I am preparing to write my master thesis.It’s about HTM hardware design and simulation data transmission by AXI on FPGA, thus I need to write some similar machine learning or devolop background about HTM.

I searched that similar machine learning information almost compare with LSTM, ELM these two, develop background goes to the biology synapse.

I want to ask if there’re more related work with HTM?

---

<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:** [May 17, 2022, 5:09pm UTC](https://discourse.numenta.org/t/related-knowledge-with-htm/9733/2 "2022-05-17T17:09:45Z")

</div>

> [@q228503](#):
>
> I want to ask if there’re more related work with HTM?

I’d add **Markov Chains** too. The learning mechanism in Markov Chains is (to my knowledge) the most structurally similar to the hebbian learning done by the TM (forming new distal dendrite segments as new patterns appear). I’m not up on the latest in Markov Chains, but I remember seeing Hidden Markov Models mentioned a lot a few years ago.

---

<div class="post-metadata">

**Author:** ![q228503](https://avatars.discourse-cdn.com/v4/letter/q/e19b73/32.png) [@q228503](https://discourse.numenta.org/u/q228503)\
**Post date:** [May 17, 2022, 8:09pm UTC](https://discourse.numenta.org/t/related-knowledge-with-htm/9733/4 "2022-05-17T20:09:52Z")

</div>

Thanks for your helping!  
I will research this topic and write something with it!

---

<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:** [May 18, 2022, 5:39am UTC](https://discourse.numenta.org/t/related-knowledge-with-htm/9733/5 "2022-05-18T05:39:15Z")

</div>

Some context: I used to work in the same research lab as @q228503. I’ve left now and he’s working on more the HW and math side of stuff (Where I’m not super familiar with). He’s building a FPGA implementation of HTM and needs some reference materials for his paper.

---

<div class="post-metadata">

**Author:** ![subutai](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/subutai/32/106_2.png) [@subutai](https://discourse.numenta.org/u/subutai)\
**Post date:** [May 23, 2022, 9:08pm UTC](https://discourse.numenta.org/t/related-knowledge-with-htm/9733/6 "2022-05-23T21:08:36Z")

</div>

Hi,

You may be interested in these papers:

> **[Neuromorphic Architecture for the Hierarchical Temporal Memory](https://ieeexplore.ieee.org/document/8620601)**
>
> A biomimetic machine intelligence algorithm that holds promise in creating invariant representations of spatiotemporal input streams is the hierarchical temporal memory (HTM). This unsupervised online algorithm has been demonstrated on several...

> **[Neuromorphic System for Spatial and Temporal Information Processing](https://ieeexplore.ieee.org/document/9109629)**
>
> Neuromorphic systems that learn and predict from streaming inputs hold significant promise in pervasive edge computing and its applications. In this article, a neuromorphic system that processes spatio-temporal information on the edge is proposed....

Many years ago we wrote a paper; part of it compared HTMs to LSTMs. You can read about that here:

> **[Continuous Online Sequence Learning with an Unsupervised Neural Network Model](https://direct.mit.edu/neco/article/28/11/2474/8502/Continuous-Online-Sequence-Learning-with-an#.WC4U8TKZMUE)**
>
> Abstract. The ability to recognize and predict temporal sequences of sensory inputs is vital for survival in natural environments. Based on many known properties of cortical neurons, hierarchical temporal memory (HTM) sequence memory recently has...

Hope this helps,

Subutai