A few months ago I read an article saying DARPA had issued one of their
requests for proposal for a neuromorphic computing architecture. I thought
the request was extremely interesting because it was asking for proposals
for how to build a system that was capable of Hebbian like learning and
Eric,
You have made a series of fantastic allegations, and I asked what evidence
you had for them, and all you provide is that you have experienced them
while under the influence of drugs.
I hope --- for your sake --- that for at least some percent of your weekly
existence you are sober
But that in no way means your statements are correct descriptions of
external reality, as many of your statements would appear to claim to be.
And you have provided no evidence, other than drug induced experience within
your own mind, that they are.
Ed Porter
The notions of correct
All I've tried to impress is that these revelations, epiphanies,
theophanies or what-have-you are at least as primary as the sensations
associated with daily life. I am tempted to compare the problem to
that of many people speaking about one microscope no-one can access.
If the issue is what you
On Thu, Nov 27, 2008 at 12:42 PM, Eric Burton [EMAIL PROTECTED] wrote:
All I've tried to impress is that these revelations, epiphanies,
theophanies or what-have-you are at least as primary as the sensations
associated with daily life.
I tend to agree ... but unless you are going to tie these
Singularity is a good home for it. Kind of a panicked digression ,_,
---
agi
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/
Modify Your Subscription:
--- On Thu, 11/27/08, Ed Porter [EMAIL PROTECTED] wrote:
http://www.eetimes.com/news/latest/showArticle.jhtml?articleID=212200673
...
If this technology pans out, it could make AGI's one
whole hell of a lot cheaper to build.
Maybe. HP's technology is based on titanium dioxide doped with
2008/11/27 Matt Mahoney [EMAIL PROTECTED]:
This is probably not a serious problem for neural networks because the
connections could be written in parallel. It's actually much faster than the
write times in the human brain, probably 10^4 seconds in the hippocampus and
10^8 seconds in the
--- On Thu, 11/27/08, Philip Hunt [EMAIL PROTECTED] wrote:
2008/11/27 Matt Mahoney [EMAIL PROTECTED]:
This is probably not a serious problem for neural
networks because the connections could be written in
parallel. It's actually much faster than the write times
in the human brain,