Hi,
Both Moshe and Ben have touched on as aspect of this discussion that I
have been thinking about for some time.
Moshe said, "I don't think that nodes+links are very good for reasoning
about vision and space..." and Ben responded "I'll say now that neurons
are basically nodes and synapses are b
to bcc list
If you wish to join this discussion, you are invited to join the AGI
list by going to the bottom of the page www.realai.net and entering his
e-mail address in the box handily provided there ;)
Perhaps a discussion between the knowledge scientists will occur here, over
the next few wee
Just to clarify:
Ben said:
"However, I'll say now that neurons are basically nodes and synapses are
basically links, so it's clear that a node-link data structure in itself
isn't way off..."
The point that Pribram and other similar minded cognitive neuroscientists
make is that the neuron is NOT
Moshe,
Here is a response to your question on how to represent visual information
in an AGI system ... followed by some more general comments on
incorporating vision in early-stage AGI systems...
Computer vision is not something I anticipate working on in the next couple
years, but it's still
I typed
> A) PixelInstanceNodes, whose TruthValues represents stimulus... and whose
> location [if needed] is represented via relations like
>
> EvaluationLink location P (5,7)
It should have been
EvaluationLink location (P ,(5,7))
since EvaluationLinks take two argument, the first one a predi
Tony Lofthouse wrote:
> Is there any value in having nodes located in a virtual n-dimensional
> space?
>
> One of the advantages that artificial systems have over biological
> systems is that the cost of long distance links/synapses is no more
> expensive that short distance connections. (Where c
Paul Prueitt wrote:
> The point that Pribram and other similar minded cognitive neuroscientists
> make is that the neuron is NOT the processing unit. It is the receptive
> fields that form a sensor array and then it is neuronal assembles and
> regional functional units (such as frontal lobes).
On Thu, 2002-10-31 at 01:12, Tony Lofthouse wrote:
>
> In a biological brain closely associated neurons are 'generally' close
> to each other physically. Whilst, artificial nodes and links are
> generally not.
>
> For me this seems to lose a whole layer of information. The patterns
> related to
> On Thu, 2002-10-31 at 01:12, Tony Lofthouse wrote:
> >
> > In a biological brain closely associated neurons are 'generally' close
> > to each other physically. Whilst, artificial nodes and links are
> > generally not.
> >
> > For me this seems to lose a whole layer of information. The patterns
A few people have asked me offline about archiving of agi list messages
I set this up via mail-archive.com, but unfortunately, I set it up a little
late, it missed the first few messages:
http://www.mail-archive.com/agi%40v2.listbox.com/
A full archive is kept internally at www.listbox.com, but
Paul,
I'd be curious if you could comment on how your concept of "process
compartments"
http://www.bcngroup.org/area3/pprueitt/pch.htm
applied to computer vision in an AGI context...
ben
---
To unsubscribe, change your address, or temporarily deactivate your subscription,
please go to
On Thu, 2002-10-31 at 11:24, Ben Goertzel wrote:
>
> But, a connection topology that tends to have a lot of local connections is
> not the same as one that really maps a 2D or 3D space, with the precision
> desired for processing spatial input data...
For us, even though the accumulated data str
> But that ignores another point worth mentioning, which is most sensory
> data the human brain works with is one-dimensional even though we don't
> think of it that way. Audio, for example, is perceived as a
> one-dimensional signal that is analyzed for spatial cues at a higher
> level.
It's t
I know, but this is a long story. grin.
I wish it where easier to tell this story.
-Original Message-
From: [EMAIL PROTECTED] [mailto:owner-agi@;v2.listbox.com]On
Behalf Of Ben Goertzel
Sent: Thursday, October 31, 2002 4:40 PM
To: [EMAIL PROTECTED]
Subject: RE: [agi] Spatial Reasoning: M
14 matches
Mail list logo