Chaos/reservoir computing and sequential cognitive models like HTM

[Bitking]

@robf

If that’s a fair representation, the randomness followed by selection reminds me of Gerald Edelman’s “neural Darwinism”. I believe Edelman won a Nobel Prize for understanding the immune system produced random variations and selected in this way. It seems he proposed cognition did the same. Teams around him made robots Darwin I-IV(?)

Rob,
I have been posting about this on the forum for years. This may have all been while you “were away” but I think you might be very interested in some of what I have been putting down.

First things first - you really REALLY have to read this online book. Darwinism plays a predominant role in computation this book, and chaos theory is mentioned. Don’t cheat, read the whole thing:

THE CEREBRAL CODE by William H. Calvin (MIT Press 1996)

Based on the proposals there, I added lateral connections to HTM to implement Calvin tiles well before Numenta added TBT to the HTM canon.

See this post for mixing the ideas of Calvin with basic HTM:

HTM Mini-Columns into Hexagonal Grids!

Or at least some wild conjectures to provoke thought! This post assumes that you are familiar with basic HTM theory and are conversant with the concepts of SDRs and HTM minicolumns. May I be so bold: [HTM%20and%20GRIDS] First - let’s be clear what I am and am not talking about. This is about cells that work by forming regular hexagonal grid structures and are not necessarily the same thing as the “grid cells” that are coding some spatial aspect of the surrounding environment. These grid-fo…

In a nutshell, this replaces the HTM spatial pooler with hexagonal coding, or more properly, Calvin tiles.

If you have missed my posts I have a digest of the more important ones on this thread:

Basic system level diagram of the brain

HTM seeks to model and understand what is going on in your head. I tossed this drawing together from memory so it is sure to be missing some connections. I skipped the thalamic connections all together as this was already a very complicated drawing. Also not shown are the connections between the limbic system and the stream passing through the brain stem and the cerebellum. These are important but not necessary to illustrate the basic cortical/limbic data flows. The blue maps are cortex compose…