Cognitive computing: Building a machine that can learn from experience
http://www.physorg.com/news148754667.html
===[ Rafael C.P. ]===
---
agi
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member
http://bits.blogs.nytimes.com/2008/11/20/hunting-for-a-brainy-computer/
===[ Rafael C.P. ]===
---
agi
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/
Modify Your Subscription
Even if he wants fault tolerance (from "cell" damage) through redundancy?
=====
Rafael C.P.
=
On Wed, Oct 15, 2008 at 9:06 PM, Matt Mahoney <[EMAIL PROTECTED]> wrote:
> --- On Wed, 10/15/08, Ed Porter <[EMAIL PROTECTED]> wrote:
>
> > Given N neural
If ruby is an option, maybe this is a solution:
http://rforum.andreas-s.net/. It's a hybrid web forum + mailing list.
Alternatively you can do the same with YahooGroups or GoogleGroups, but they
haven't all the common web forum functionalities.
=====
I'm in the same situation as Joseph and I agree with him. I think almost
everything mailed here is useful in some way, but a division would be fine
so we can focus on what is more important to us.
=
Rafael C.P.
=
On Wed, Oct 15, 2008 at 3:49 PM, Joseph Henry <[EMAIL P
There are a lot of mathematical proofs of convergence of ANN's and GA's,
just look for the original papers about them. IOW, everything contradicts
that.
=====
Rafael C.P.
=
On Wed, Oct 8, 2008 at 6:36 PM, Valentina Poletti <[EMAIL PROTECTED]>wrote:
> And here is
| Modify Your Subscription
>
>
>
> --
> Ben Goertzel, PhD
> CEO, Novamente LLC and Biomind LLC
> Director of Research, SIAI
> [EMAIL PROTECTED]
>
> "If men cease to believe that they will one day become gods then they
> will surely become worms."
.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/?&;
--
=
Rafael C.P.
=
-
This list is sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/?member_id=231415&user_secret=e9e40a7e
s to our every potential action. But my
point is: we do it extremely crudely - more crudely than I'm aware any
program does.
- Original Message -
From: "Rafael C.P."
> In RL there's no need to assign values to everything, they are derived
> from the basic values
sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/?&;
--
=
Rafael C.P.
=
-
This list is sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/?member_id=231415&user_secret=e9e40a7e
"Reinforcement learning is a simple theory that *only* solves problems
for which we can design value functions."
In other words... almost anything in real life...
-
This list is sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listb
/www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/?list_id=303
--
=
Rafael C.P.
=
-
This list is sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/?list_id=303
12 matches
Mail list logo