On 8/6/06, Richard Loosemore <[EMAIL PROTECTED]> wrote:
> This is the one thing I am not so sure of: I think the idea of
> "predicate logic" carries a lot of baggage with it, which is likely to
> cause systems built that way to have convergence problems (decreasing
> stability and intelligence as the system scope is expanded to include
> higher proportions of grounded, autonomously acquired concepts, and as
> the period of standalone functioning is increased) that we are only just
> beginning to understand.
>
> My feeling is that something similar to predicate logic is required,
> which will look like PL under some circumstances, or when viewed from a
> distance, but which when looked at closely will not be PL at all.
>
> I'm working on it. (As hard as I can, though not by any means full
> time, alas).
> "predicate logic" carries a lot of baggage with it, which is likely to
> cause systems built that way to have convergence problems (decreasing
> stability and intelligence as the system scope is expanded to include
> higher proportions of grounded, autonomously acquired concepts, and as
> the period of standalone functioning is increased) that we are only just
> beginning to understand.
>
> My feeling is that something similar to predicate logic is required,
> which will look like PL under some circumstances, or when viewed from a
> distance, but which when looked at closely will not be PL at all.
>
> I'm working on it. (As hard as I can, though not by any means full
> time, alas).
Some features of predicate logic may be obsolete, for example, the fact that I cannot modify a predicate with another predicate, but have to use reification. But the basic idea of predicate logic is sound -- the world made up of objects, relations, properties -- this is very basic stuff. I think predicate logic + probability would suffice for AGI, perhaps with fuzziness as well. Logic alone without numbers, would be brittle.
Anyway, I'd be eager to hear about your theory later =)
YKY
To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
