A recent Google talk on memory systems which might have some relevance
for people designing AGI systems.
http://www.youtube.com/watch?v=2Ei6wFJ9kCc
Here the guy is basically describing how supervised and unsupervised
learning complement each other in order to overcome problems such as
On Friday 21 December 2007 09:51:13 pm, Ed Porter wrote:
As a lawyer, I can tell you there is no clear agreed upon definition for
most words, but that doesn't stop most of us from using un-clearly defined
words productively many times every day for communication with others. If
you can only
Bob, Thanks for the link. Ed Porter
-Original Message-
From: Bob Mottram [mailto:[EMAIL PROTECTED]
Sent: Saturday, December 22, 2007 8:30 AM
To: agi@v2.listbox.com
Subject: [agi] Combined memory systems
A recent Google talk on memory systems which might have some relevance
for people
For those interested in automated theorem-proving,
I'm pleased to announce a major advance in tools
has occurred...
The Mizar library of formalized math has finally
been translated into a sensible format, usable
for training automated theorem-proving systems ;-)
Josef Urban informed me that
On Dec 14, 2007 9:07 AM, Benjamin Goertzel [EMAIL PROTECTED] wrote:
Just to be clear: I am sure that mindreading technology is coming,
it's your relative
timing estimate that perplexes me...
Wasn't me that said it, but...
If we define mindreading as knowing whether someone is telling the
Oh - I haven't read the report, but I did look into the state of the
art of BCI several months ago. Some things I remember:
- Arrays can receive pulses from at most 100 neurons.
- Wireless devices don't have enough bandwidth to transmit the pulses
from more than about 100 neurons. Even doing
On Dec 22, 2007 8:15 PM, Philip Goetz [EMAIL PROTECTED] wrote:
Dawkins trivializes religion from his comfortable first world perspective
ignoring the way of life of hundreds of millions of people and offers little
substitute for what religion does and has done for civilization and what has