# Is HTM multi-step prediction currently possible?

**URL:** <https://discourse.numenta.org/t/is-htm-multi-step-prediction-currently-possible/3929>\
**Category:** Numenta Theory\
**Created:** [May 19, 2018, 11:07am UTC](https://discourse.numenta.org/t/is-htm-multi-step-prediction-currently-possible/3929 "2018-05-19T11:07:24Z")\
**Posts on this page:** 1\
**Showing post:** 1

<div class="post-metadata">

**Author:** ![sebjwallace](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/sebjwallace/32/6411_2.png) [@sebjwallace](https://discourse.numenta.org/u/sebjwallace)\
**Post date:** [May 19, 2018, 11:07am UTC](https://discourse.numenta.org/t/is-htm-multi-step-prediction-currently-possible/3929/1 "2018-05-19T11:07:24Z")

</div>

In current implementations as far as I know the cells in a region can predict one step ahead. But in this [paper](https://numenta.org/resources/HTM_CorticalLearningAlgorithms.pdf) it explains that a region can predict multiple steps ahead.

> As mentioned earlier, predictions are not just for the next time step. Predictions in  
> an HTM region can be for several time steps into the future. Using melodies as  
> example, an HTM region would not just predict the next note in a melody, but might  
> predict the next four notes. This leads to a desirable property. The output of a  
> region (the union of all the active and predicted cells in a region) changes more  
> slowly than the input. Imagine the region is predicting the next four notes in a  
> melody. We will represent the melody by the letter sequence A,B,C,D,E,F,G. After  
> hearing the first two notes, the region recognizes the sequence and starts predicting.  
> It predicts C,D,E,F. The “B” cells are already active so cells for B,C,D,E,F are all in one  
> of the two active states. Now the region hears the next note “C”. The set of active  
> and predictive cells now represents “C,D,E,F,G”. Note that the input pattern changed  
> completely going from “B” to “C”, but only 20% of the cells changed. **Page 25**

I am wondering about how a region achieves this. It has been made clear exactly how one-step prediction is achieved, but it would be interesting how a region can predict an arbitrary number of steps into the future.

I have a vague memory that it is achieved through temporal pooling? Something like an SDR is layer 3 remains stable because it is associated with all the TM SDRs of a sequence in layer 4? Then that stable representation is projected back to layer 4 to make the multi-step prediction.

Maybe I’m missing something in the paper that explains this, or maybe its still just a high-level theory?

---

_[View the full topic](https://discourse.numenta.org/t/is-htm-multi-step-prediction-currently-possible/3929)._