From newshub.ccs.yorku.ca!ists!torn!utcsri!rutgers!cs.utexas.edu!sdd.hp.com!ux1.cso.uiuc.edu!mp.cs.niu.edu!rickert Tue Jun 23 13:21:14 EDT 1992
Article 6314 of comp.ai.philosophy:
Path: newshub.ccs.yorku.ca!ists!torn!utcsri!rutgers!cs.utexas.edu!sdd.hp.com!ux1.cso.uiuc.edu!mp.cs.niu.edu!rickert
>From: rickert@mp.cs.niu.edu (Neil Rickert)
Newsgroups: comp.ai.philosophy
Subject: Re: 5-step program to AI
Message-ID: <1992Jun18.205639.3093@mp.cs.niu.edu>
Date: 18 Jun 92 20:56:39 GMT
References: <60840@aurs01.UUCP> <1992Jun18.022002.29912@mp.cs.niu.edu> <60842@aurs01.UUCP>
Organization: Northern Illinois University
Lines: 117

In article <60842@aurs01.UUCP> throop@aurs01.UUCP (Wayne Throop) writes:
>> rickert@mp.cs.niu.edu (Neil Rickert)
>> The computer symbols you are thinking of are those used within the
>> computer, or between the computer and nearby peripherals. 
>
>Well... no, actually.  I was thinking about (say) strings of ascii
>characters that are emitted from computer peripherals for humans to
>interpret.  I'm pretty sure we were talking about the same thing.
>
>> The central property of digital communications is that a signal can
>> be significantly degraded, but as long as it is not degraded past the
>> point where it can be recognized, it can be accurately recreated.  It
>> is this resistance to signal degradation that is so important.
>
>Yes, but that wasn't what I was getting at.  The notion I was
>responding to was that since the difference between humans and other
>mammals is use of abstract symbols, and since computers already use
            ^^^
  There is some confusion here.

  You raised a question about the composition of symbols (in terms of
the atomic components, and you raised a question about use of symbols.
You are now treating my response on composition as if it were the
response on use.

>I think that may well be wrong, because "use abstract symbols" may
>mean very different things when applied to humans as when applied
>to computers.  In fact, I tend to think that the two *are* very
>different things, and it *won't* be easy to go from general-mammal
>to human capabilities.

  There is no question that computers use symbols very differently from
the way humans use them.  I never argued otherwise.  Both are used to
represent information, but the human ability to represent information
symbolically is very different from the computers.  What I did claim was
that the abilities needed for this representation of semantic information
are already present in the chimpanzee, so that the EXTRA needed beyond
the chimp is only the ability to construct a large extensible set of
symbols.

>> This brings us right back to the importance of pattern recognition.  The
>> computer chess program and the human chess player both proceed in a
>> somewhat similar manner.  They construct possible sequences of continuation
>> moves and evaluate the result. 
>
>I think this is incorrect.  The evidence I've seen is that computers
>generate zillions of continuations and evaluate each result.

 So far this does not disagree with my point, that both generate
continuations and evaluate the result.  You omitted the rest of my
statement where I said that the method of evaluation is very different.
All that is necessary for chess playing is to generate the next move.
Generating extra moves beyond that is only necessary when needed to
evaluate the possible next move.  The human method, based on pattern
recognition (of such patterns as control of the center of the board,
momentum, etc) is generally quite distinctly superior, so very few
continuation moves are needed for an adequate evaluation.  The methods of
evaluation by computer program are much cruder, so many more steps are
needed.

>                                                              Humans,
>on the other hand, generate a small handfull of continuation moves and
>this set *happens* *to* *contain* the "right" moves, and then spend
>most of their time deciding between them by detailed comparision (not
>by pattern recognition).

  How do you think these comparisons are being made, if there is no
pattern recognition?  Just counting pieces lost is usually not good
enough.  You have to see what you will control after the move being
tested.

>                           In some as-yet-unknown way, the good moves
>were constructed, rather than being the recognized among the bad
>moves.

  The good moves were constructed because the pattern recognition abilities
of the human player enabled him to rapidly dismiss many pieces as being
not relevant to the next move.

>Human pattern-recognition cycle times are tens, maybe hundreds of
>trials per second.  There just isn't time to fit tree searches of the
>depths humans actually do into the time they actually take, by
>recognizing "right" moves among the zillions possible.

  Who said anything about tree searches?  I certainly didn't.  You are
reading things into my reply which were never intended to be there.

>                                                        Thus, pattern
>recognition in the usual sense can't really be involved here either
>(though it may be related in some way, eg: pattern recognition schemata
>used in some sort of generative process).

  I'm not talking about "pattern recognition in the usual sense" as you
term it.  I have very carefully used the term "pattern recognition" rather
than "pattern matching".  We don't know how humans manage to be so good
at pattern recognition, but I seriously doubt that it is by means of a
(structured or unstructured) comparison (i.e. matching) with prerecorded
patterns.

>It is still possible that some parallelism is being exploited, and
>humans consider all-moves-at-once and recognize where the good ones are
>in some "move-space".

  In last year's fighting against Iraq, I didn't hear of our military
planners doing simulations involving moving ships around in the
antarctic either.  Using our abilities of pattern recognition, the
human player quickly recognizes where the action is, and concentrates
on moves which affect that area.  Occasionally a player can be fooled by
a clever deception.  But the best players acquaint themselves with the
playing style of their opponents, and this background information is
contextual background to their pattern recognition.

>Anyway, labling what's going on in the human case as anything like
>"pattern recognition" is very, very premature, at best.

  Maybe.  But at least I am putting something on the table for you to
try to shoot down.


