On 15/06/06, arnoud [EMAIL PROTECTED] wrote:
On Thursday 15 June 2006 21:35, Ben Goertzel wrote:
If this doesn't seem to be the case, this is because of that some
concepts are so abstract that they don't seem to be tied to
perception
anymore. It is obvious that they are (directly) tied
HI,
So my guess is that focusing on the practical level for building an agi
system is sufficient, and it's easier than focusing on very abstract
levels. When you have a system that can e.g. play soccer, tie shoe lases,
build fences, throw objects to hit other objects, walk through a terrain
to
Ben:
As for the prediction paradigm, it is true that any aspect of
mental activity can be modeled as a prediction problem, but it
doesn't follow that this is always the most useful perspective.
arnoud I think it is, because all that needs to be done is achieve
arnoud goals in the future. And
Eric Baum wrote:
It is demonstrably untrue that the ability to predict the effects of
any action, suffices to decide what actions one should take to
reach one's goals.
For example, given a specification of a Turing machine, one can
predict its sequence of states if one feeds in any particular
Novamente is modular software-wise, but very far from modular
cognition-wise
This makes sense, particularly in light of your further explanation about
the effects of replacing the PLN module with AnotherPI module, but I would
think that it should be solvable by being thorough about tagging
Eric Baum wrote:
It is demonstrably untrue that the ability to predict the effects of
any action, suffices to decide what actions one should take to
reach one's goals.
For example, given a specification of a Turing machine, one can
predict its sequence of states if one feeds in any particular
This is more cog-sci than AGI oriented, but it's interesting...
http://www.physorg.com/news69338070.html
New analysis of the language and gesture of South America's
indigenous Aymara people indicates they have a concept of time
opposite to all the world's studied cultures -- so that the past
In Hawkins' HTM architecture it can be imagined that each node contains an
action proposal system. And that actions (and goals) of a node are formulated
in terms of the concepts that are present at that node, and then that those
actions are pushed down the hierarchy were they cause more concrete
More cool stuff...
-- Forwarded message --
From: Neil H. [EMAIL PROTECTED]
Date: Jun 16, 2006 5:22 PM
Subject: Paper: Inducing savant-like counting abilities with rTMS
To: [EMAIL PROTECTED]
(x-posted to extropy-chat)
Back in 2003 there was a popular-press article on Allan
The Science channel(193 Dishnetwork) has some shows that some of our AGI
people might like.
Sat:
Incredible Robots-The Evolution of Robots.
The brain processes Visual images.
Galapagos: Beyond Darwin.
Sun:
Some Physics shows:
Part of the Universe is Missing: String theory,
10 matches
Mail list logo
