Re: virus: kurzweil cuts the mustard

Robin Faichney (robin@faichney.demon.co.uk)
Sat, 2 Jan 1999 10:17:28 +0000

In message <002301be35e0$a2c330c0$e2194018@CS1000568-A.cgno1.ab.wave.hom e.com>, David McFadzean <morpheus@lucifer.com> writes
>
>-----Original Message-----
>From: Robin Faichney <robin@faichney.demon.co.uk>
>To: virus@lucifer.com <virus@lucifer.com>
>Date: Friday, January 01, 1999 2:17 PM
>Subject: Re: virus: kurzweil cuts the mustard
>
>
>>Nope. There's no reason it has to be a lookup table.
>>Any kind of symbolic reasoning and/or neural nets is
>>allowed.
>
>That doesn't change anything. For any symbolic reasoning
>program or neural net, there is an equivalent lookup
>table that will produce identical behavior.

I'm assuming that it can learn, so if we're talking about an extendable lookup table, you're right. But that point I'm trying to make is that a machine, of whatever sort, has no reason to be more limited in its responses than we are. 

-- 
Robin