Re: [MLUG - DISCUSSION] Re: [MLUG] AI - any suggestions?

[Kmicic <EMAIL:PROTECTED>]

"Igor Izyumin Jr." wrote:

> their memory.  Basically, if I say that thing about the cars, the brain does
> some analysis and figures it out.  Following is my idea of how it does it.

that'll make you the 1st person who knows how brain figures things out!
but i think i know what you meant... basically how you'd go about
designing a system to do this kind of analysis. i agree with you, this
is a very complex subject. a discussion in the intro to AI book on doing
parsing for a 3 sentence universe is 20 odd pages long and it doesnt
even begin to scratch on those matters. however, the kinds of problems i
described have been solvable since the 60s (or maybe even before that),
so that's why i refered to it as "simple task."

> As you can see, it is VERY, VERY complex.  You have to have a complex neural
> net for that, and the most complex neural nets that exist now do not have
> anything close to this capability.  It requires a HUGE amount of memory, a

hmm... i don't see where you got the idea for using a neural net to
solve this task...? predicate logic seems to be the only way. i honestly
don't see much use for neural nets in nlp.

> duplicate.  Then, the system would need to be fed an enourmous amount of
> information (just think how much data a human accumulates and stores by the
> age of 2 and how little the human can do intellectually at that point).  I
> would be surprised if I saw somebody create a system remotely close to this
> within the next 50 years.  And Michael appears to think that it can be done
> with a few perl scripts.

you don't have to make a wholesome natural language parser on your first
try. i assumed this discussion pertained to limited domains.

/paul
--
To unsubscribe, go to http://mlug.missouri.edu/members/edit.php

Archives are available at http://mlug.missouri.edu/list-archives/