Path: utzoo!attcan!utgpu!jarvis.csri.toronto.edu!clyde.concordia.ca!uunet!wuarchive!zaphod.mps.ohio-state.edu!sunybcs!boulder!bill
From: bill@boulder.Colorado.EDU
Newsgroups: comp.ai.neural-nets
Subject: Re: back-prop NNs and `SAS' regression!
Message-ID: <15039@boulder.Colorado.EDU>
Date: 19 Dec 89 18:58:30 GMT
References: <220700005@uxe.cso.uiuc.edu> <44929@bu-cs.BU.EDU>
Sender: news@boulder.Colorado.EDU
Reply-To: bill@synapse.Colorado.EDU (Bill Skaggs)
Organization: University of Colorado, Boulder
Lines: 22

>
> There are two distinct reasons for studying neural nets, the primary
> reason is to gain insights into the mechanisms of natural
> intelligence.  The secondary reason is that SOMETIMES neural nets can
> solve problems more elegantly.  When this is the case, then it's
> appropriate to use them.
> 

  The secondary reason (IMHO) is that neural nets are massively parallel.
When one has reached the limits of sequential speed, one must go to
parallelism in order to get greater power.  Neural nets are unlikely to
ever provide especially _elegant_ solutions to very many problems:  their
virtue is that they provide a brutal and simplistic solution that sometimes
(surprisingly) actually works.  
  
  I don't expect neural network methods to be practical until massively
parallel VLSI neural network chips exist and are easily obtainable.  At
that point the advantages of parallelism will compensate for the crudity
of the method for some applications, and the revolution will truly begin.
The day is not yet here, but it can't be too much longer in coming.

							Bill Skaggs