Newsgroups: comp.robotics
Path: brunix!cat.cis.Brown.EDU!agate!howland.reston.ans.net!swrinde!news.dell.com!tadpole.com!uunet!ftpbox!mothost!pts-nntp!tseserv!RedKnight
From: RedKnight@tseserv (RedKnight)
Subject: Re: 100 Billion Nuerons
Message-ID: <Ct9E95.86I@pts.mot.com>
Sender: mccarley@tseserv (RedKnight)
Nntp-Posting-Host: tseserv
Organization: Motorola Inc, Paging Products Group, Boynton Beach, FL
References: <ZByDPc2w165w@sfrsa.com> <Csw2xD.G9F.3@cs.cmu.edu>
Date: Wed, 20 Jul 1994 21:55:52 GMT
Lines: 42

In article <Csw2xD.G9F.3@cs.cmu.edu>, hpm@cs.cmu.edu (Hans Moravec) writes:
> 
> Brad Smallridge, bsmall@sfrsa.com writes
> re accumulating neural inputs over time:
> >
> >I'm not sure. When I originally thought of this kind of system
> >I assumed I would need a mechanism to bleed off the counters.
> >What a pain though because you would need to touch every cell
> >in the system periodically. Another way is to somehow time stamp
> >the cells counters and when a new stimulus comes into the cell,
> >you ask if the old counter value is too old, and make a decision
> >based on the count and how old the count is.
> > 
> >I'm thinking now that you really don't need to bleed off the 
> >counters at all. So what if a seldom visited cell ocassionally 
> >goes off. In the grand scheme of things, this once in a great 
> >while shouldn't effect the outcome of the thinking process. It's
> >the cells that are firing a lot that really matter.
> 
> Another possibility is to do the "bleed" probabilistically.  Decrement
> just a few of the cells, chosen at random, or on some scrambled round
> robin schedule.  The slower the bleed rate, the fewer cells you need
> to touch each cycle.
> 
> 			-- Hans Moravec   CMU Robotics
> 

Assuming one is stuck with a digital single-CPU implementation, it still
seems that a system of any size would justify a Cellular Automata
approach.  In this case, the inherent clock tick would allow each automata
to adjust its integration sum probabilistically or using any other
schedule of choice.  In other words, the integrated sum would degrade
over time, not necessarily linearly, but independent of input activity.

-- 
  \ /                            | 
 --O===<|  RedKnight             |
  / \      mccarley@pts.mot.com  |

..   .... .- ...- .   ... . . -.   - .... .   ..-. ..- - ..- .-. .
.- -. -..   .. -   .. ...   .- . ..- .-. .- .-..   .-.-.-

