Create 3 Layer HTM Network for one sensor

[rhyolight]

Object Pool

Proximal input: sensory layer
Distal input: neighboring object pool layers
Represents: current object

Sensory Layer

Proximal input: sensory feature
Distal input: location from Location Layer / temporal context
Represents: feature at a location in object space

This layer needs to receive distal input in two ways: from itself as in the typical SP/TM operation defined in HTM School, and from the Location Layer. These distal inputs must be mixed.

Location Layer

Proximal input: displacement representing movement
Represents: location in 2D envrionment

When new proximal input representing movement is applied, GCM bumps move from current location to predicted location.

[rhyolight]

Putting this here because even if we have not written the logic for the layers, we can still figure out how to hook up the network.

[rhyolight]

In NuPIC we have code that creates the network described above: https://github.com/numenta/htmresearch/blob/master/htmresearch/frameworks/location/location_network_creation.py

[codeallthethingz]

That NuPIC file has great comments and ascii art!

[Zbysekz]

We need TM without internal distal synapses.
Proceeding in htm-community/htm.core#852