X-Message-Number: 26136
From: 
Date: Thu, 5 May 2005 07:26:39 EDT
Subject: Re: CryoNet #26119 To T. Donaldson.

From T. Donaldson:

> Hello Mr Bozzonetti again:
> 
> Your answer f ails once more. You forgot that the neuron is new and 
> therefore may not be on any table. Moreover you once more want to put
> some number of neurons on the same chip. Ridiculous and even worse,
> if you were ever to actually make such a system, disappointing.

I don't understand that garbage, where come from that idea of a new neuron 
not registered on any table?

If two neurons make a new synaptic link, as I have said, a new entry in the 
table is added, if one of the neuron is new, creating it is mostly creating 
addresses in the different tables for it.

A modern chip will simulate a neuron block (may be 1,000 individual neurons) 
in 0.001% of its time, why did you insist that the processor must remains idle 
99.999 % of the time ?

Yvan Bozzonetti.


 Content-Type: text/html; charset="US-ASCII"

[ AUTOMATICALLY SKIPPING HTML ENCODING! ] 

Rate This Message: http://www.cryonet.org/cgi-bin/rate.cgi?msg=26136