wolframscience.com

A New Kind of Science: The NKS Forum : Powered by vBulletin version 2.3.0 A New Kind of Science: The NKS Forum > Pure NKS > Numenta HTM training and NKS
  Last Thread   Next Thread
Author
Thread Post New Thread    Post A Reply
Enexseenge

Kingston WA

Registered: Mar 2005
Posts: 46

Numenta HTM training and NKS

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?

__________________
A great revolution is at hand, but this is just a metaphor.

Report this post to a moderator | IP: Logged

Old Post 12-10-2007 06:03 AM
Enexseenge is offline Click Here to See the Profile for Enexseenge Click here to Send Enexseenge a Private Message Click Here to Email Enexseenge Visit Enexseenge's homepage! Edit/Delete Message Reply w/Quote
tomjones


Registered: Not Yet
Posts: N/A

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

Report this post to a moderator | IP: Logged

Old Post 12-10-2007 02:31 PM
Edit/Delete Message Reply w/Quote
Enexseenge

Kingston WA

Registered: Mar 2005
Posts: 46

Htm

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).

__________________
A great revolution is at hand, but this is just a metaphor.

Report this post to a moderator | IP: Logged

Old Post 12-10-2007 04:57 PM
Enexseenge is offline Click Here to See the Profile for Enexseenge Click here to Send Enexseenge a Private Message Click Here to Email Enexseenge Visit Enexseenge's homepage! Edit/Delete Message Reply w/Quote
Jason Cawley
Wolfram Science Group
Phoenix, AZ USA

Registered: Aug 2003
Posts: 712

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).

Report this post to a moderator | IP: Logged

Old Post 12-10-2007 10:20 PM
Jason Cawley is offline Click Here to See the Profile for Jason Cawley Click here to Send Jason Cawley a Private Message Edit/Delete Message Reply w/Quote
tomjones


Registered: Not Yet
Posts: N/A

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

Report this post to a moderator | IP: Logged

Old Post 12-12-2007 09:56 PM
Edit/Delete Message Reply w/Quote
Jason Cawley
Wolfram Science Group
Phoenix, AZ USA

Registered: Aug 2003
Posts: 712

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...

Report this post to a moderator | IP: Logged

Old Post 12-13-2007 03:31 PM
Jason Cawley is offline Click Here to See the Profile for Jason Cawley Click here to Send Jason Cawley a Private Message Edit/Delete Message Reply w/Quote
Post New Thread    Post A Reply
  Last Thread   Next Thread
Show Printable Version | Email this Page | Subscribe to this Thread


 

wolframscience.com  |  wolfram atlas  |  NKS online  |  Wolfram|Alpha  |  Wolfram Science Summer School  |  web resources  |  contact us

Forum Sponsored by Wolfram Research

© 2004-14 Wolfram Research, Inc. | Powered by vBulletin 2.3.0 © 2000-2002 Jelsoft Enterprises, Ltd. | Disclaimer | Archives