How does HTM recognize thousands of objects of the real world?

[Bitking]

I had the same general issues. JH addressed some of them here:

1000 Brains Theory Q&A

You cover a lot of topics in this post. I will try to answer several of them. Let me start with what we mean by the “sensor fusion problem.” We humans have a unified perception of the world. This is derived from a large number of inputs from different sensory modalities. When the inputs arrive in the neocortex they are expanded. The million fibers from the retina become tens of millions of fibers leaving V1. V2 is even bigger. The concept of an “image” is immediately lost, as the representation…

I see that Numenta is describing a transformation of feature space to an object space as part of lower-level processing. Not complete objects - but the part of the object that can be sensed locally.

The difference is very subtle but it emphasizes a different way of thinking about what the columns are doing with the top-down information stream.

For me personally - it’s still features but they are framed and parsed by the top-down flow.

Or I still have no clue - it could go either way!