Hi,

> > My contention is that the incremental approach will take
> unacceptably long
> > to generate the compounds needed to solve nontrivially complex practical
> > problems.
>
> We don't have to start from atoms --- most compounds in our mind are
> obtained through interaction with other people. We just build upon them. I
> don't think it is realistic to build an AI system to generate
> compound terms
> with arbitrary complexity.

I agree that we build up compounds hierarchically, building new ones from
old; and also that we get some compounds via learning from other people.

And of course, generating new compound terms with arbitrary complexity is
unrealistic.  Thus the hierarchy heuristic -- there is a low bound on the
complexity of new compound terms the mind can discover, so the mind has to
build new terms from previously learned ones, etc.

However, I don't think this bound is QUITE so low that it can be met by
purely incremental learning  methods...

> You assume that only the best result matters, and the bad ones don't hurt.
> It is not always the case. If I'm going to make decisions about
> my life, I'd
> rather have ten average ones, but not a perfect and nine terribly
> bad ones.

Hmmm...  Pei, maybe this personality difference explains why my life has
been considerably more dramatic than yours!!! ;-)

> > I think this aspect of NARS is like a kind of stochastic hill-climbing.
> > Because I think NARS is not going to keep (P AND Q) in its active memory
> > very long if it's not judged as "good" by the system.  Is it?  How does
> > NARS, in the current conception, decide what to keep around and what not
> > to?
> > What am I misunderstanding here?
>
> You are close --- under resources restriction, the system has to omit
> certain possibilities, which is the case for Novamente, too. The
> difference
> is just to decide what to omit. In NARS, the decision is experience based.
> No doubt many good opportunities are lost, but unless we assume we somehow
> know the future, I don't think we can avoid that.

In Novamente, the decision is also experience based.  As I said in my other
email, evolutionary learning is just a particular form of experience-based
learning.  The question is not whether learning is experience-based, but
rather, how cleverly one takes account of experience!

-- Ben


-------
To unsubscribe, change your address, or temporarily deactivate your subscription, 
please go to http://v2.listbox.com/member/[EMAIL PROTECTED]

Reply via email to