Re: Loosemore's Proposal

From: rpwl@lightlink.com
Date: Mon Oct 24 2005 - 16:48:57 MDT


Michael Wilson wrote:
> Richard Loosemore wrote:
>>First-principles research in FAI? You don't have a workable
>>theory of FAI, you just have some armchair speculation.
>
>
> I don't have such a theory nor am I working on one. But formal
> theories of this calibre do not pop out of the ether fully
> formed. They are the result of years of hard work on a progressive
> series of precursors, which I /can/ observe the SIAI steadily
> making progress on. I expect that you would write off the entire
> field of theoretical physics as useless 'armchair speculation', or
> at least you would if you could find a way to ignore the successes
> of that discipline.

Sigh!

All this (including the rest of your message, which I have omitted) is
predicated on a misunderstanding of the point I am trying to make. I
cannot count the number of times this has happened just in the last couple
of messages from you. This happened last time I raised issues of this sort,
and it is happening again, so here is the point, stated as bluntly as I can:

There is a REASON why one should build a reasonably complete system,
watching the learning mechanisms *really* build concepts (and not rely on
you the programmer to insert them) and watching the recognition system
*really* figure out the relationship between sensory patterns and
recognized internal concepts (rather than have you assume that this can be
done later..... and that REASON is that we (CAS-inspired cognitive science
people) have substantial empirical data that says that if you invent your
local mechanisms and don't test them in the above way, those mechanisms may
simply not EVER work, no matter how much fiddling you do with them. Until
you understand how that could be so, and that that is the reason for my
proposal, your other comments are just interesting starting points for
debates on unrelated issues.

Richard Loosemore

---------------------------------------------
This message was sent using Endymion MailMan.
http://www.endymion.com/products/mailman/



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:52 MDT