For many kinds of purposes, a better (and vastly faster) approach is to
grow a network fabric between the two networks in a kind of soft
merge. Not quite as smart as a true merge in theory, but if the two
networks have been training on somewhat orthogonal classes of
information, may have a
Hi Shane,
I understand your perspective and I think it's a reasonable one.
I think that what you'll get from this approach, if you're lucky, is a kind
of primitive brain, suitable to control something with general
intelligence around that of a reptile or a very stupid mammal.
Then, you can use
Hi Ben,
Thanks for the comments.
I understand your perspective and I think it's a reasonable one.
Well your thinking has surely left it's mark on my views ;-)
I think that what you'll get from this approach, if you're lucky, is a kind
of primitive brain, suitable to control something with
Shane,
Yes, this is the basic idea. Some structures and dynamics will tend
to categorize and cluster information, some will tend to recognize
temporal patterns, some might tend to store information, some will
be mixtures of these things. Exactly what I'll find is hard to know
in advance.
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]
Behalf Of Shane Legg
Sent: Wednesday, March 03, 2004 6:25 PM
To: [EMAIL PROTECTED]
Subject: Re: [agi] Complexity of Evolving an AGI
Ciao,
Is something weird going on with the AGI list here? I just got two
emails
Ben Goertzel wrote:
But the different trials need not be independent --- we can save the
trajectory of each AI's development continuously, and then restart a new
branch of AI x at time y for any recorded AI x at any recorded time point
y.
Also, we can intentionally form composite AI's by
Secondly, fusion of two trained AIs may be a very costly
procedure. I'm beginning to study this topic and it seems
that the complexity is generally polynomial with small
exponents such as O(n^3) but with EXTREMELY large n's
like 1 billion. I'm mainly studying ANNs, maybe other
architectures
But the different trials need not be independent --- we can save the
trajectory of each AI's development continuously, and then restart a new
branch of AI x at time y for any recorded AI x at any recorded time point
y.
Also, we can intentionally form composite AI's by taking portions of AI x's
