On 10/4/07, J Storrs Hall, PhD <[EMAIL PROTECTED]> wrote:
> On Thursday 04 October 2007 11:52:01 am, Vladimir Nesov wrote:
> > Analogy-making can be reformulated as other problems, so even if it's
> > not named this way it's still associated with many approaches to
> > learning. Recalling relevant knowledge is about the same thing as
> > analogy-making, and in lifelong learning almost all knowledge comes
> > from past experience, so perception of current scene consists of
> > recalling refined elements of this experience.
> >
> > So, could you elucidate on why do you specifically address analogy-making?
>
> If I have the primitive "make an analogy between A and B" I can use it as a
> subroutine in "recall the memory that makes the best analogy to X" and it
> seems simpler than trying to do it the other way around.
>

Somewhat, but requirement to search in huge long term memory can be
important for algorithm choice. Apart from this use case, you may want
to find recurring patterns within a given scene, which is equivalent
to finding the best analogy to one part of the scene in the rest of
the scene (and with right representation you don't even need to do
that).

Anyway, my point was not that view on analogy-making as recall is
'better', but that analogy-making problem lives in that incarnation,
so absence of explicitly stated analogy-making research doesn't mean
that problem is neglected.

-- 
Vladimir Nesov                            mailto:[EMAIL PROTECTED]

-----
This list is sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/?member_id=8660244&id_secret=50115516-e0d3df

Reply via email to