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 > Applied NKS > Sequence Recognition
  Last Thread   Next Thread
Author
Thread Post New Thread    Post A Reply
AlirezaNejati


Registered: Jun 2006
Posts: 2

Sequence Recognition

I'm thinking perhaps a cellular automaton (or network system or any other kind of simple program) could be used to recognize sequences.
What I mean is to use some kind of system to learn sequences of characters (abcdbca for example), as they occur in a serial fashion through time (first a comes, then b, etc.) and recognize them upon seeing them, and then classify them according to the frequency they appear.
I don't know what kind of system would be useful for such a thing, but I'm sure that some kind of simple program can cut it.
Any ideas, people?

__________________
Nothing can be made from nothing.
-Lucretius

Report this post to a moderator | IP: Logged

Old Post 10-20-2006 06:44 PM
AlirezaNejati is offline Click Here to See the Profile for AlirezaNejati Click here to Send AlirezaNejati a Private Message Click Here to Email AlirezaNejati Edit/Delete Message Reply w/Quote
T. Walliczek

Left of London

Registered: Jul 2005
Posts: 4

Who or what is doing the "learning"? This is still a big hurdle in AI. I can dig up some links if you are thinking machine learning?

Report this post to a moderator | IP: Logged

Old Post 06-06-2007 09:06 AM
T. Walliczek is offline Click Here to See the Profile for T. Walliczek Click here to Send T. Walliczek a Private Message Click Here to Email T. Walliczek Edit/Delete Message Reply w/Quote
Philip Ronald Dutton
independent
Columbia, SC

Registered: Feb 2004
Posts: 172

alternative

You might want to read about hierarchical temporal memory as describe by the numenta group. It is a model for how the neocortex of the human brain might work when recognizing sequences.

Here is a link to some material:

http://www.numenta.com/Numenta_HTM_Concepts.pdf

Also, check out some www.numenta.com.


If you are serious about recognizing sequences via computers, the HTM paradigm is important for cross study.


Enjoy.

Also, there is an HTM engine available for download.

__________________
P h i l i p . R . D u t t o n

Report this post to a moderator | IP: Logged

Old Post 06-08-2007 11:45 PM
Philip Ronald Dutton is offline Click Here to See the Profile for Philip Ronald Dutton Click here to Send Philip Ronald Dutton a Private Message Visit Philip Ronald Dutton's homepage! Edit/Delete Message Reply w/Quote
Philip Ronald Dutton
independent
Columbia, SC

Registered: Feb 2004
Posts: 172

Sequence recognition

By default, the elementary CA rules are already performing sequence recognition albeit on a small scale. I think the original post is considering macro-recognition.

__________________
P h i l i p . R . D u t t o n

Report this post to a moderator | IP: Logged

Old Post 06-10-2007 09:48 PM
Philip Ronald Dutton is offline Click Here to See the Profile for Philip Ronald Dutton Click here to Send Philip Ronald Dutton a Private Message Visit Philip Ronald Dutton's homepage! Edit/Delete Message Reply w/Quote
Todd Rowland
Wolfram Research
Maryland

Registered: Oct 2003
Posts: 113

While it is not completely clear what is being asked for in this thread, some work has been done to use Cellular automata for hashing.

More autonomous sorts of learning strategies have involved the creation of basins of attraction (e.g. p.1101) and a slightly different approach is outlined in chapter 10 (seep.624).

Report this post to a moderator | IP: Logged

Old Post 06-11-2007 08:44 PM
Todd Rowland is offline Click Here to See the Profile for Todd Rowland Click here to Send Todd Rowland a Private Message Click Here to Email Todd Rowland 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  |  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