Hello, I'm a singularity/agi enthusiast and have been reading on the subject
for a couple of years.
I hope It's ok to ask questions on this forum (that it's not specifically
for opencog/novamente).
What do you think of Geoff Hinton's wake-sleep neural networks in his paper
To recognize shapes,
On 8/13/08, rick the ponderer [EMAIL PROTECTED] wrote:
Reading this, I get the view of ai as basically neural networks, where
each individual perceptron could be any of a number of algorithms
(decision tree, random forest, svm etc).
I also get the view that academics such as Hinton are trying
On 8/13/08, YKY (Yan King Yin) [EMAIL PROTECTED] wrote:
On 8/13/08, rick the ponderer [EMAIL PROTECTED] wrote:
Reading this, I get the view of ai as basically neural networks, where
each individual perceptron could be any of a number of algorithms
(decision tree, random forest, svm etc).
On 8/13/08, rick the ponderer [EMAIL PROTECTED] wrote:
Thanks for replying YKY
Is the logic learning you are talking about inductive logic programming.
If so, isn't ilp basically a search through the space of logic programs (i
may be way off the mark here!), wouldn't it be too large of a search
On Wed, Aug 13, 2008 at 4:14 AM, rick the ponderer [EMAIL PROTECTED] wrote:
Thanks for replying YKY
Is the logic learning you are talking about inductive logic programming. If
so, isn't ilp basically a search through the space of logic programs (i may
be way off the mark here!), wouldn't it
There is a another reason why embodied agi is useful. That is because
the challenge will provide some discipline for the programmer who
might otherwise never confront the structural problems that I believe
are fundamental to the problem of developing genuine agi.
Jim Bromer
YKY asked:
I'm interested in how the the rules are fetched from memory, and how the
variables get instantiated, etc...
How would you represent the given facts:
John is male
John is unmarried
and then perform the inference to get
John is a bachelor?
Sorry if this sounds too
On 8/13/08, Ben Goertzel [EMAIL PROTECTED] wrote:
But if one doesn't need to get into implementation details, in the
simplest case one just has
VariableScopeLink X
ImplicationLink
___ANDLink
__ InheritanceLink X male
__ InheritanceLink X Unmarried
___InheritanceLink X bachelor
How do you interact with, and how does your idea of advanced AGI act without
being embodied?
I dont see how it can without being embodied (VR at least), *to some extent*,
and the more embodied, the more complicated actions that can be allowed.
A personal assistant AGI could be attached to a
Well I think I agree with you to the extent that you recognize that
virtual reality can act as a kind of embodiment and that the features
that are significant to AG in such a system would be the potential for
interrelated complexity. But, with an advanced AGI capable of genuine
learning, the same
I just realized that my emails have been ignored by the list-serv, which
explains the stunning silence I had received for all my earlier posts. It's
probably for the best :
In any case, here's a repost of my introduction. That was both delayed, and
is also no longer overdue, since my earlier
Interesting article on the discovery of the connection between dopamine,
reinforcement learning and social neuroscience in a recent Seed Magazine
article:
Evolution essentially bootstrapped our penchant for intellectual concepts
to the same reward circuits that govern our animal appetites.
Email lists are all very well, but I must confess that I've been primed by
thousands of years of evolution for the exchange of ideas via aural
dissemination in a real time environment. And preferably around a camp fire
accompanied by some kind of burnt animal meat on a stick and a fermented
On Wed, Aug 13, 2008 at 5:04 AM, Jim Bromer [EMAIL PROTECTED] wrote:
There is a another reason why embodied agi is useful. That is because
the challenge will provide some discipline for the programmer who
might otherwise never confront the structural problems that I believe
are fundamental
Pieces of rat brain controls small robo platform. How's *that* for an
out-of-body experience! There's video even!!
http://technology.newscientist.com/channel/tech/mg19926696.100-rise-of-the-ratbrained-robots.html
Cheers,
Brad
P.S. Sorry I haven't been participating on the list that much
On Wed, Aug 13, 2008 at 3:16 PM, Jonathan El-Bizri [EMAIL PROTECTED] wrote:
On Wed, Aug 13, 2008 at 5:04 AM, Jim Bromer [EMAIL PROTECTED] wrote:
There is a another reason why embodied agi is useful. That is because
the challenge will provide some discipline for the programmer who
might
A 'Frankenrobot' with a biological brain
Meet Gordon, probably the world's first robot controlled exclusively by
living brain tissue.
Article at
http://www.breitbart.com/article.php?id=080813192458.ud84hj9hshow_article=1
---
agi
Archives:
[agi] Meet the world's first robot controlled exclusively by living brain
tissueThanks, Ed. My casual impression is that the scientist here, Kevin
Warwick, is un peu d'un nut - although skilled at self-publicising. Some years
ago, he had a chip sewn into his arm. He was going to open doors with
Mike,
Thanks for the heads up. Maybe the project will go nowhere.
But to me the fact that he has been able to create any sort of neural net
with 50K to 100K nodes, with presumably a potential connectivity as high at
human neurons (i.e., upto 10K synapses) is impressive.
Presumably
19 matches
Mail list logo