[Numenta HTM training and NKS] - A New Kind of Science: The NKS Forum

A New Kind of Science: The NKS Forum

Pages:1


Numenta HTM training and NKS

(Click here to view the original thread with full colors/images)


Posted by: Enexseenge

I have a very simple question, simply looking for people who have been exploring analyzing the data produced by class 4 CA systems with new technologies.

Has anyone experimented with HTM (Hierarchical Temporal Memory) systems to analyze data produced by class 4 CA systems?


Posted by: tomjones

To what end would you use a memory model to analyze class 4 CA? HTM is a way of modeling parts of the human brain, its not realy a tool for analysis like a fourier transform...

Thanks


Posted by: Enexseenge

I have very little experiance in modeling anything and basic computer programming skills. Besides this point i have been researching HTM and the Numenta software technology and while reading through on the algorithm which these HTM systems use i simply had the idea come into my head that an actively evolving class 4 CA could be used as a data set to train the system in real time, perhaps...

Not sure exactly what this would lead to but... such novel ideas arise within my mind, lacking the experiance and skills necessary to have a deep level of understanding the phenomena (class 4 CA and the analysis of it).


Posted by: Jason Cawley

Actually, HTMs aren't really models of human intel, though the design is motivated by certain features ascribed to human intel by the designers (whether true of human intel or not). They are really a cross between Bayesian networks for machine learning and neural nets. As such, they are indeed general transforms or more exactly, classifiers, that one can imagine throwing at any kind of data, to see what the method manages to make of that data.

The obvious thing to try to do with them in NKS would be to make a CA rule recognizer, in the sense of trying to train an HTM to discriminate among different CA rules (the top level outputs that would count as success being, "this is a rule n pattern", "that is a rule m pattern"). Visual pattern recognition is what they are most developed at doing, really - they are largely an attempt to extend the success of NNs at static pattern recognition, to recognition of objects in various views, by incorporating a time domain and different scales. Well, you would just feed them data from simple CA rules, slightly more complex ones from simple initials (rule 90, rule 225, etc), then complex ones from simple, etc.

As for class 4s specifically, one might hope an HTM could recognize particles in relatively "thin" versions of them, mostly repeating background I mean. It would be a fair test of what is claimed for them - though not earth shattering in what it might show us about CAs.

Has it been worked on? I think not. Some have worked on CA methods for pattern recognition, and have fed CA images and textures to standard pattern recognition AI routines - that is about as close as it gets, in terms of stuff already done (as far as I know, obviously).


Posted by: tomjones

To be honest you are better off making your own rather then adapting that one, actually the math is really not that hard, and if you use mathematica or matlab you can do a lot of it yourself for cheap. Quite honestly if this type of patter recognition interests you there is a whole field of formal research that is out their and for applications such as CA there are probably simpler solutions to the problem due to the type of visuals CA generates.

Thanks


Posted by: Jason Cawley

Well no one would want one just to recognize CA patterns, as though that were a hard technical task. It is just a test case to see how the things work...




Forum Sponsored by Wolfram Research

© 2004-2008 Wolfram Research, Inc. | Powered by vBulletin 2.3.0 © 2000-2002 Jelsoft Enterprises, Ltd. | Disclaimer
vB Easy Archive Final - Created by Xenon and modified/released by SkuZZy from the Job Openings