How is a unique room being represented and associated with locations?

[nick]

An accurate location of space is represented by the concatenation of all the grid cell modules.
How is this representation being associated to a unique room?
How is a unique room being represented?

[rhyolight]

An accurate location of space is represented by the concatenation of all the grid cell modules.

This is a bit misleading. I was trying to show how GCMs could be used to represent space with SDRs, but that is not exactly how we use them in HTM theory. I suggest you read the paper: Locations in the Neocortex: A Theory of Sensorimotor Object Recognition Using Cortical Grid Cells.

[Bitking]

@nick
I invite you to think about ratslam and how that concept could be coded with the collection of different types of cells that are found in the HC/EC complex.

RatSLAM uses grid cell techniques to map subdivision

Check out the answer by Ajit Rajasekharan. Very nice answer: https://www.quora.com/What-are-the-major-differences-between-grid-cells-and-place-cells-and-why-do-we-need-them-both What does this have to say to SDR and HTM? First - think of the hippocampus as a sort of encoder for time and space. Patient HM shows that this is not the space where long-term memory is stored but we can’t form these without the hippocampus. Grid/place/boundary/path/head direction are all things that are parsed out …

Also - and this is a bit of a stretch - what would happen if the information underwent a transformation before coding like I am describing here:

Encoding vision for HTM

Ratslam has used scene recognition using a FFT filtered strip view. I find the results to be surprisingly effective in a cluttered office environment.

Encoding vision for HTM

I don’t know how strong your background is in algorithms and various coding techniques but I will try to keep this as general as possible considering the source material. In the ratslam, they use some observed organization of the hippocampus. The body of the hippocampus and related entorhinal cortex are known to encode the environment as responses in “grid cells” - cells that fire in relation to where a critter is in a given environment. This grid pattern varies in spacing as you go from front…