From newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.ecf!utgpu!cs.utexas.edu!sun-barr!ames!haven.umd.edu!darwin.sura.net!convex!constellation!a.cs.okstate.edu!onstott Tue Mar 24 09:55:29 EST 1992
Article 4439 of comp.ai.philosophy:
Path: newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.ecf!utgpu!cs.utexas.edu!sun-barr!ames!haven.umd.edu!darwin.sura.net!convex!constellation!a.cs.okstate.edu!onstott
>From: onstott@a.cs.okstate.edu (ONSTOTT CHARLES OR)
Newsgroups: comp.ai.philosophy
Subject: Re: Definition of Understanding
Message-ID: <1992Mar12.233311.22489@a.cs.okstate.edu>
Date: 12 Mar 92 23:33:11 GMT
References: <AdjWsY600UzxM1dYIJ@andrew.cmu.edu> <1992Mar12.155333.26748@gpu.utcs.utoronto.ca>
Organization: Oklahoma State University, Computer Science, Stillwater
Lines: 36

In article <1992Mar12.155333.26748@gpu.utcs.utoronto.ca> pindor@gpu.utcs.utoronto.ca (Andrzej Pindor) writes:
>In article <AdjWsY600UzxM1dYIJ@andrew.cmu.edu> fb0m+@andrew.cmu.edu (Franklin Boyle) writes:
>>Andrzej Pindor writes:
>>
>>I don't see why an artificial neural net would not in principle be able
>>to have an intrinsic capacity for reference, but current neural networks
>>(say, of the layered, feed-forward type) are physical pattern matching 
>>systems, just as digital computers are.  The only difference is that
>>matchers for the latter are deliberately programmed whereas the former
>>are trained, meaning that connection strengths (sets of which constitute
>>matchers) are adjusted according to input and output values.
>>
>You still have not answered my question how do you imagine humans to recognize
>patterns withouth matching them to something. You repeatedly point out that
>computers (digital or neural networks) are 'physical pattern matching systems'
>but how is it different from what human brains do?
  Tell me what a new born baby does?  What sort of pattern matching goes
on in child development that would indicate to you that there exist a
"physical pattern matching system" that is the same as in a computer?

Thanks.

BCNya,  
  Charles O. Onstott, III


------------------------------------------------------------------------
Charles O. Onstott, III                  P.O. Box 2386
Undergraduate in Philosophy              Stillwater, Ok  74076
Oklahoma State University                onstott@a.cs.okstate.edu


"The most abstract system of philosophy is, in its method and purpose, 
nothing more than an extremely ingenious combination of natural sounds."
                                              -- Carl G. Jung
-----------------------------------------------------------------------


