# Learning long-range dependencies

**URL:** <https://discourse.numenta.org/t/learning-long-range-dependencies/3979>\
**Category:** Numenta Theory\
**Created:** [June 2, 2018, 2:40pm UTC](https://discourse.numenta.org/t/learning-long-range-dependencies/3979 "2018-06-02T14:40:00Z")\
**Posts on this page:** 1\
**Showing post:** 5

<div class="post-metadata">

**Author:** ![TaherHabib](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/taherhabib/32/2895_2.png) [@TaherHabib](https://discourse.numenta.org/u/TaherHabib)\
**Post date:** [June 1, 2020, 1:39pm UTC](https://discourse.numenta.org/t/learning-long-range-dependencies/3979/5 "2020-06-01T13:39:27Z")

</div>

> [@sunguralikaan](#):
>
> Temporal Memory ™ can be configured such that the current active cells representing B at time _t_ , not only form connections to the previously active cells at time _t-1_ (last event of x) but also to the cells prior to that ( _t-n_ ).

Hi,

Could you please elaborate on how this configuration of TM might look like? I have found this discussion on using [graded SDRs](https://discourse.numenta.org/t/graded-non-binary-sdrs/3776) to improve [random access of SDRs](https://discourse.numenta.org/t/alternative-sequence-memory/3898) quite helpful. Does your answer relate to this in anyway?

I would really appreciate any help on this matter since I am studying the problem of learning long-range dependencies in HTM, using the cases of Extended and Continual Reber Grammars. Thanks 🙂

---

_[View the full topic](https://discourse.numenta.org/t/learning-long-range-dependencies/3979)._