# HTM Implementation

**URL:** <https://discourse.numenta.org/t/htm-implementation/4910>\
**Category:** NAB\
**Created:** [November 8, 2018, 1:19pm UTC](https://discourse.numenta.org/t/htm-implementation/4910 "2018-11-08T13:19:47Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![kourosh](https://avatars.discourse-cdn.com/v4/letter/k/97f17d/32.png) [@kourosh](https://discourse.numenta.org/u/kourosh)\
**Post date:** [November 8, 2018, 1:19pm UTC](https://discourse.numenta.org/t/htm-implementation/4910/1 "2018-11-08T13:19:47Z")

</div>

Hello  
I am new in HTM. I have tried to use NAB as a part of implementation in my thesis but got confused as I saw python codes. Is there any instruction which shows how to implement NAB??

---

<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:** [November 8, 2018, 4:36pm UTC](https://discourse.numenta.org/t/htm-implementation/4910/2 "2018-11-08T16:36:44Z")

</div>

NAB is not an HTM implementation, it is a benchmark. Please read [this](https://numenta.com/machine-intelligence-technology/numenta-anomaly-benchmark/).

---

<div class="post-metadata">

**Author:** ![kourosh](https://avatars.discourse-cdn.com/v4/letter/k/97f17d/32.png) [@kourosh](https://discourse.numenta.org/u/kourosh)\
**Post date:** [November 9, 2018, 8:25am UTC](https://discourse.numenta.org/t/htm-implementation/4910/3 "2018-11-09T08:25:19Z")

</div>

Thank you dear Matt

It was a misunderstanding by me. I have to change my question.  
I checked different parts of nupic files like encoders, anomaly.py, anomalylikelihood.py and… but I got confused how to use them as a part of my thesis implementation. Now I want to know is there any instruction about it or is it just related to understanding python code and learn how to use them??

thanks in advance

---

<div class="post-metadata">

**Author:** ![jimmyw](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/jimmyw/32/1485_2.png) [@jimmyw](https://discourse.numenta.org/u/jimmyw)\
**Post date:** [November 9, 2018, 10:55am UTC](https://discourse.numenta.org/t/htm-implementation/4910/4 "2018-11-09T10:55:04Z")

</div>

I’d recommend getting familiar with HTM theory first, starting with HTM School on youtube. I say this because it’s useful to understand the biological context of the algorithm and you may not get this just by reading the source.

Even if you like to learn by reading code, you can do this alongside each episode as you go.