Re: AI Methods in Go

[Mousheng Xu <moushengxu@xxxxxxxxxxxxxxxx>]

At 06:22 PM 6/30/99 +0200, Patricia Hughes and David Elsdon wrote:
>>         A potential problem for arule based system is that you may have
too many
>> rules, and you don't know how to prioritize them. Resolving too many rules
>> may take up a lot of computation time.
>
>This is unlikely to be true even with thousands of rules. Many AI/KBS
applications
>are built using production rule systems. As a result of this, a let of
effort has
>gone into making these systems very powerful and very quick. There is a
lot of
>literature available on this subject - if you want references just ask.

	You are right at this point. One point what I actually meant was the
"conceptual" difficulty beyond the technical difficulty. You have so many
rules, assuming not all rules are independant, then finding the
relationship among the rules might not be so easy.
	I used CLIPS for pattern matching, but it could not handle a large size (a
couple of thousands?) of pattern base. I guess it could handle 1 thousand
rules easily.
	Well, KBS is a good way to try.

	Good luck.

-- Mousheng Xu