To allow the htm.core temporal memory to learn sequences effectively, it is import to understand the impact of the different parameters in more detail.
In this part I will introduce
Temporal Memory – Previously on this blog…
Part 1 just covered enough basics of htm.core to get us started, and we actually saw how the single order memory got trained.
A cycle of encoded increasing numbers from 0 to 9 was very easy to predict, as there was always just one specific value that could follow the … more
To make it easier to get started with some of my htm.core experiments or with htm.core in general, I thought it would make sense to provide a docker image with htm.core preinstalled. So here it is:
Please welcome the htm.core-jupyter image.
This image is using the scipy-notebook as foundation, with the htm.core package installed on top of it.
For a list of the other preinstalled python packages, just look here.
There are also a lot of other Jupyter docker images available. I recommend starting with the Jupyter Docker Stacks quick start page for a … more
I came across the concept of Hierarchical Temporal Memory (HTM) and its implementation a while ago, and am still very fascinated about this approach to artificial intelligence.
When, about one year ago, the active development shifted towards the community fork named htm.core, which supports Python 3, it became finally time to have a closer look and try it out by myself.
BTW: According to this forum post, there are no plans to upgrade the older NuPIC library to Python 3.
A lot of documentation about the theory of HTM is available at numenta.org… more