# HTM does’t work at all！

**URL:** <https://discourse.numenta.org/t/htm-does-t-work-at-all/7615>\
**Category:** Getting Started\
**Created:** [June 2, 2020, 10:38am UTC](https://discourse.numenta.org/t/htm-does-t-work-at-all/7615 "2020-06-02T10:38:36Z")\
**Posts on this page:** 1\
**Showing post:** 10

<div class="post-metadata">

**Author:** ![Bitking](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/bitking/32/3099_2.png) [@Bitking](https://discourse.numenta.org/u/Bitking)\
**Post date:** [June 9, 2020, 12:04pm UTC](https://discourse.numenta.org/t/htm-does-t-work-at-all/7615/10 "2020-06-09T12:04:21Z")

</div>

HTM works very well.  
See:

> [@HTM Working Memory](https://discourse.numenta.org/t/htm-working-memory/7642/3):
>
> @Sparse HTM memory works by pattern completion. Many neural models work the same way and there is a considerable amount of theory to back up the utility of this computing model. Very few (none?) also handle temporal memory Each map in the sheet of columns has (potentially) a vast number of overlapping learned temporal/spatial patterns. When the perception is registered the saved pattern that most closely resembles the sensed pattern is recalled. There is some parsing to distribute these memori…

---

_[View the full topic](https://discourse.numenta.org/t/htm-does-t-work-at-all/7615)._