Numbers for humans vary rather a lot. Some types of cells have up to
200,000 connections (Purkinje neurons) while others have very few.
Thus talking about the number of synapses per neuron doesn't make
much sense. It all depends on which type of neuron etc. you mean.
Anyway, when talking about
Mike,
But interestingly while you deny that the given conception of intelligence
is rational and deterministic.. you then proceed to argue rationally and
deterministically.
Universal intelligence is not based on a definition of what rationality is.
It is based
on the idea of achievement. I
OK, here I think is the simplest test of adaptivity that cuts right to the
heart of the matter, and provides the most central measure of ADAPTIVE (i.e.
DIVERGENT) intelligence as distinct from CONVERGENT, algorithmic intelligence.
My assumption: your system has this agent/guy moving around a
@ Mike: remember that she wasn't blind/deaf from birth - read her
autobiographical account (available on project gutenberg - which is an
excellent corpus source btw - also available on DVD :) for how he
finally hooked up the concept of words as tokens for real world
concepts when linking the word
Ah.. I didn't get the test quite right. It isn't simply how many alternative
ways can you find of achievng any goal?
You might have pre-specified a vast number of ways of moving from A to B for
the system.
The test is: how many NEW (non-specified) alternative ways can you find of
achieving
My assumption: your system has this agent/guy moving around a home/office
environment. [Adjust question accordingly if not]
He has a simple task: Move from A to B or D. But the normal answer Walk
it is for whatever reason no good, blocked.
The simple test is this: how many alternative ways of
What is harder is as follows: if goals G1 and G2 look to be related, and
the system has learned a bunch of ways to fulfill G1; then, this latter fact
should make it easier for the system to find ways to fulfill G2 (than if it
hadn't learned ways to fulfill G1 already). This is known as transfer
Shane:
According to Ben Goertzel, Ph. D, Since universal intelligence is only
definable up to an arbitrary constant, it's of at best ~heuristic~ value in
thinking about the constructure of real AI systems. In reality, different
universally intelligent modules may be practically applicable to
Just kidding ;-)
-- Forwarded message --
From: Robin Lee Powell [EMAIL PROTECTED]
Date: Apr 29, 2007 2:58 AM
Subject: About the wierdest mail I've ever received. [
[EMAIL PROTECTED]: confidential and revolutionary message]
To: [EMAIL PROTECTED]
Here's me giving up on the
On 4/29/07, Benjamin Goertzel [EMAIL PROTECTED] wrote:
To use another pragmatic example, both LISP and FORTRAN have universal
computing power, but, some programs are **way** shorter to code in LISP than
FORTRAN, and this makes a big practical difference. Even though it's true
that
length(P in
Ben,
Are you claiming that the choice of compiler constant is not pragmatically
significant in the definition of the Solomonoff-Levin universal prior, and
in Kolmogorov
complexity? For finite binary sequences...
I really don't see this, so it would be great if you could elaborate.
In some
I think that the hardest part
to finding a solution to a difficult problem often lies in finding the
right way to
view the problem, in order words, the right representation.
Cheers
Shane
Yes ... but, what this means is that a critical task of AGI design is to be
sure
your AGI has, or has
On 4/29/07, Benjamin Goertzel [EMAIL PROTECTED] wrote:
Holding a new computer at your home such as myself will take very
little space( less than 2 square meters) and this will never waste
your time (you can use your new computer whenever you want) and you
will be of course able to continue your
On 4/29/07, Mike Tintner [EMAIL PROTECTED] wrote:
He has a simple task: Move from A to B or D. But the normal answer Walk
it is for whatever reason no good, blocked.
Disambiguate-
1. Move from starting point A to either B or D
2. Move from either A to B or take another option D
I feel we
Mike Dougherty wrote:
On 4/29/07, Mike Tintner [EMAIL PROTECTED] wrote:
He has a simple task: Move from A to B or D. But the normal answer
Walk
it is for whatever reason no good, blocked.
Disambiguate-
1. Move from starting point A to either B or D
2. Move from either A to B or take another
Er sorry.
The ambiguity arises because I wanted the journey to be a reasonable
distance...let's say through two or three rooms/ corridors or more - a
distance where a range of solutions like those proposed - use a scooter/
have s.o. carry you in a wheelbarrow ... would be relevant - as
Again, in bold blue below.
Original Message -
From: YKY (Yan King Yin)
To: agi@v2.listbox.com
Sent: Sunday, April 29, 2007 1:01 AM
Subject: Re: [agi] rule-based NL system
Mark,
I need to know a bit more about your approach. What do you mean when you
say grammar is
Has this approach been successful for any lesser animals? E.g.; has anyone
simulated an insect brain system connected to a simulated insect body in a
virtual environment? Starting with a mouse brain seems a bit ambitious.
Since I haven't posted on the list before I guess I should introduce
I think someone at UCLA did something similar for lobsters. This was
used as material for an SF story (Lobsters, Charles Stross[sp?])
Jan Mattsson wrote:
Has this approach been successful for any lesser animals? E.g.; has anyone
simulated an insect brain system connected to a simulated
On 4/29/07, Richard Loosemore [EMAIL PROTECTED] wrote:
The idea that human beings should constrain themselves to a simplified,
artificial kind of speech in order to make life easier for an AI, is one
of those Big Excuses that AI developers have made, over the years, to
cover up the fact that
Mike,
There is something fascinating going on here - if you could suspend your
desire for precision, you might see that you are at least half-consciously
offering contributions as well as objections. (Tune in to your constructive
side).
I remember thinking that you were probably
21 matches
Mail list logo
