John, (01)
It doesn't bother me that in your system the "encoding and the
semantic distance measure support many different kinds of
applications." What I like is that you base your analysis on the
retrieval of examples, encoded as graphs or anything else. That
enables you to make as many distinctions as you have examples. (02)
This relates to the complexity point I have been trying to make all
the way through this thread. (03)
My argument has been that for many systems there are more ways of
generalizing examples than there are examples. This is a game changing
assumption. Up to now it has always been assumed that there will be
fewer generalizations than examples (rules, classes, etc.) At worst
that you need to make one generalization per example (analogy.) If it
is possible to make more generalizations than examples, the game
changes completely. No one set of generalizations will suffice. (04)
The only way to model that would be to base analysis on sets of examples. (05)
I understand once you have retrieved graphs your processing varies,
but have you tried generating analyses based on sets of graphs
retrieved? (06)
-Rob (07)
On Mon, Oct 6, 2008 at 5:14 PM, John F. Sowa <sowa@xxxxxxxxxxx> wrote:
> Rob,
>
> The basis for the analogy engine is a graph encoding that supports
> efficient
> storage
> and retrieval of arbitrary graphs based on a semantic distance measure.
>
> That encoding and the semantic distance measure support many different
> kinds of
> applications, of which analogies are one important kind. But there are an
> open
> ended
> number of different ways of using the technology, and there are more left
> to
> explore
> than the ones we have implemented so far.
>
> In any case, I'm in travelling mode for the next two weeks, so I will only
> have
> sporadic access to email.
>
> John (08)
_________________________________________________________________
Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/
Subscribe/Config: http://ontolog.cim3.net/mailman/listinfo/ontolog-forum/
Unsubscribe: mailto:ontolog-forum-leave@xxxxxxxxxxxxxxxx
Shared Files: http://ontolog.cim3.net/file/
Community Wiki: http://ontolog.cim3.net/wiki/
To Post: mailto:ontolog-forum@xxxxxxxxxxxxxxxx (09)
|