# TemporalMemory running very slow after long training

**URL:** <https://discourse.numenta.org/t/temporalmemory-running-very-slow-after-long-training/5052>\
**Category:** Engineering\
**Tags:** sequence-memory\
**Created:** [December 12, 2018, 3:29am UTC](https://discourse.numenta.org/t/temporalmemory-running-very-slow-after-long-training/5052 "2018-12-12T03:29:50Z")\
**Posts on this page:** 3\
**Page:** 3

<div class="post-metadata">

**Author:** ![dmac](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/dmac/32/5842_2.png) [@dmac](https://discourse.numenta.org/u/dmac)\
**Post date:** [February 7, 2019, 1:18pm UTC](https://discourse.numenta.org/t/temporalmemory-running-very-slow-after-long-training/5052/41 "2019-02-07T13:18:28Z")

</div>

> [@Paul\_Lamb](#):
>
> I’m not sure about NuPIC specifically […]
> 
> HTM can be implemented without doing this. Instead of sampling from the receiving segments, you can update via pointers on the transmitting axons. Due to sparsity, this is a significant optimization. This strategy can be applied to both SP and TM.

In NuPIC the TM does what you’re talking about, by using the `Connections` class. The connections class keeps a list of input axons and where all of their synapses go to, and it efficiently distributes each active input by iterating through just the synapses which the input connects to.

The SP does not use the connections class, instead using sparse matrices. In the community fork I’ve changed the SP to use the connections class and also optimized the connections class.

---

<div class="post-metadata">

**Author:** ![vpuente](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/vpuente/32/4115_2.png) [@vpuente](https://discourse.numenta.org/u/vpuente)\
**Post date:** [February 7, 2019, 4:21pm UTC](https://discourse.numenta.org/t/temporalmemory-running-very-slow-after-long-training/5052/42 "2019-02-07T16:21:30Z")

</div>

> [@Bitking](#):
>
> I will offer that blind adherence to a strict top down or bottom up stance limits your navigation in the problem search-space.

I agree. You need both. But start from the bottom 😄

From there you need “high-level” observations/intuitions to constrain your infinite search space. Using the top as the only drive, you end with DNN v2.0 .

Using bottom as the only drive, you end with the Human Brain Project (BTW: I suggest you take a look to edX course of Markran [Simulation Neurscience](https://www.edx.org/es/course/simulation-neuroscience-epflx-simneurox). They are an incredible work… but I don’t know if the will succeed only following that route).

> [@Bitking](#):
>
> BTW: the " [Deep Predictive Learning: A Comprehensive Model of Three Visual Streams](https://discourse.numenta.org/t/deep-predictive-learning-a-comprehensive-model-of-three-visual-streams/3076)" paper postulates that this is exactly what is going on in the cortex/thalamus streams. The “forward” stream from the senses going up the hierarchy interacts with the guidance from the “reverse” pathways including the hypothalamus/thalamus/forebrain/cortex as a feedback or training signal. This is NOT the classic ANN

Thanks for the paper. I read some parts some time ago. Without investing too much time in that, my two cents is that is way too complex (and too specific). It should be easier and valid not only for vision but for any part of the cortex. I like more S.M. Sherman papers 😉

---

<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:** [February 7, 2019, 5:04pm UTC](https://discourse.numenta.org/t/temporalmemory-running-very-slow-after-long-training/5052/43 "2019-02-07T17:04:00Z")

</div>

Split this topic on February 7, 2019, 5:04pm UTC

A post was merged into an existing topic: [Deep Predictive Learning: A Comprehensive Model of Three Visual Streams](https://discourse.numenta.org/t/deep-predictive-learning-a-comprehensive-model-of-three-visual-streams/3076/8)

[Previous page](https://discourse.numenta.org/t/temporalmemory-running-very-slow-after-long-training/5052.md?page=2)