Subject:
|
Re: an idea, can someone tell me if this is possible/been done before/etc?
|
Newsgroups:
|
lugnet.robotics
|
Date:
|
Wed, 3 Dec 2003 04:37:42 GMT
|
Original-From:
|
Jim Choate <{ravage@einstein.}ihatespam{ssz.com}>
|
Viewed:
|
878 times
|
| |
|
|
On Tue, 2 Dec 2003, Steve Baker wrote:
> Gordon Elliott wrote:
> > On "complexity", I would point out that the computational power of the
> > neural pathways of the house fly thoroughly exceeds the computational
> > throughput of our most massive supercomputer clusters at the moment.
>
> That was true 20 years ago.
>
> A housefly's brain contains just 400 neurons. Your PC can easily simulate
> a 400 neuron neural network at faster update rates than biological neurons.
>
> The problem isn't the raw computational power.
Roger doger on that. I understand that C. Elegins (sp?) is the current top
project goal for this sort of stuff. Something like 10,000 neurons.
-- --
Open Forge, LLC 24/365 Onsite Support for PCs, Networks, & Game Consoles
512-695-4126 (Austin, Tx.) help@open-forge.com irc.open-forge.com
Hangar 18 Open Source Distributed Computing Using Plan 9 & Linux
512-451-7087 http://open-forge.org/hangar18 irc.open-forge.org
James Choate 512-451-7087 ravage@ssz.com jchoate@open-forge.com
|
|
Message is in Reply To:
4 Messages in This Thread:
  
 
- Entire Thread on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
|
|
|
|
