Newsgroups: comp.ai.philosophy
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!news.mathworks.com!news.ultranet.com!zombie.ncsc.mil!news.duke.edu!agate!howland.reston.ans.net!EU.net!CERN.ch!dxal18.cern.ch!hallam
From: hallam@dxal18.cern.ch (Phillip M. Hallam-Baker)
Subject: Re: What's innate? (Was Re: Artificial Neural Networks and Cognition
X-Nntp-Posting-Host: dxal18.cern.ch
Message-ID: <D38GEs.7B8@news.cern.ch>
Sender: news@news.cern.ch (USENET News System)
Reply-To: hallam@dxal18.cern.ch
Organization: Wot!!! Me ????
References: <3g6js6$fug@mp.cs.niu.edu> <1995Jan26.150315.1420@il.us.swissbank.com> <3g8sru$jsn@mp.cs.niu.edu> <1995Jan26.224354.401@news.media.mit.edu>
Date: Mon, 30 Jan 1995 19:20:51 GMT
Lines: 44


In article <1995Jan26.224354.401@news.media.mit.edu>, minsky@media.mit.edu (Marvin Minsky) writes:

|>Bah.  You cannot assess the "poverty" unless you have an idea of the
|>learning scheme.  Didn't Mitchell Marcus show that surprisingly few
|>examples were needed, if you have the right sort of representations
|>and learning algorithms?
|>
|>Furthermore, isn't it obvious that the "constraints of Universal
|>Grammar" could just as well emerge from the limitations of what the
|>learning algorithm could discover, rather than the limitations of the
|>ultimate language processor?
|>
|>I suspect this whole subject is an artifact that came from Chomsky's
|>initial separation of "competence" from, I forget what the other is.

I think it stems from attaching intent to natures `design' principles. 
Nature does not have purpose, merely structures that have a certain
behaviour. The human appendix does not have a purpose, it has a behaviour
in that when it fails it causes the owner to die.

If one develops an AI emulation of a language recognition system then intent
and hence purpose can be ascribed. But describing the result of the 
process of evolution in terms of purpose ascribes a purpose to evolution,
thus the argument is theological, not scientific.


The problem with Chomskys position is that it tries to wrap up biological
systems into neat, well ordered packages which have well defined functions.
At the very least this type of reductionism seems premature. Until we have
demonstrated that we understand the system it is far too early to become
dogmatic about the mechanism or limitations of it.

Having a nice model does not mean that a subject is understood. Natural 
systems have a peculiar way of converging towards behaviours which may be
defined with beautiful mathematical precision even when what goes on 
underneath is bizarely random. Looking at Newtons laws nobody would consider
Quantum mechanics to be `obviously' what lies underneath them. 


--
Phillip M. Hallam-Baker

Not Speaking for anyone else.
