Re: Announcement: The Temporal Neuron Revolution.... some thoughts

Article View: comp.ai

Article #9319

#9319

From: Erik Vick
Date: Tue, 14 Oct 1997 00:00

28 lines
2116 bytes

Louis Savain wrote:
> 
> In article <343AAFF1.6D35@dial.pipex.com>, Howard Snart
> <aac88@dial.pipex.com> wrote:
> 
> >[...]
> >This approach stems from several misgivings I have over the existing
> >methods of teaching neural nets... most significantly
> >backtracking.(which I see as un-scalable, and fundementally wrong... you
> >force the outputs to conform, whereas the problem may lie far from the
> >outputs)
> 
>   I agree.  Traditional neural nets are not biologically plausible,
> nor do they do the kind of learning that is needed to gain common
> sense.
> 

I am interested in knowing why a neural net must be biologically
plausible?  (Yes I'm a NN newbie)  I thought there were two accepted
methodologies of Neural Nets : 1) the biologic modeling approach and 2)
more of a functional modeling approach.

Is it your position that to gain common sense / learn, the construct
must be a biologically plausible neural net?

Regards,
Erik Vick

Technical Details

Message-ID: <34437E3B.400F@concentric.net>

Path: arc1-ca.pugleaf.net!unknown!not-for-mail

References:

<342b36de.10039603@news.earthlink.net> <342fb9ae.4111800@news.earthlink.net> <343AAFF1.6D35@dial.pipex.com> <343efdd4.28374986@news.earthlink.net>

Show Full Headers

Complete Article Headers

X-Google-Language: ENGLISH,ASCII-7-bit
X-Google-Thread: 10d5b4,10bd0b81cba64349
X-Google-Attributes: gid10d5b4,public
X-Google-Thread: 10d04f,10bd0b81cba64349
X-Google-Attributes: gid10d04f,public
X-Google-Thread: 10461e,10bd0b81cba64349
X-Google-Attributes: gid10461e,public
X-Google-Thread: f6b1a,10bd0b81cba64349
X-Google-Attributes: gidf6b1a,public
X-Google-Thread: 101fc6,10bd0b81cba64349
X-Google-Attributes: gid101fc6,public
X-Google-Thread: 10ca9b,10bd0b81cba64349
X-Google-Attributes: gid10ca9b,public
From: Erik Vick <erikvick@concentric.net>
Subject: Re: Announcement: The Temporal Neuron Revolution.... some thoughts
Date: 1997/10/14
Message-ID: <34437E3B.400F@concentric.net>
X-Deja-AN: 280388499
Distribution: inet
References: <342b36de.10039603@news.earthlink.net> <342fb9ae.4111800@news.earthlink.net> <343AAFF1.6D35@dial.pipex.com> <343efdd4.28374986@news.earthlink.net>
To: savainl@earthlink.net
Organization: Concentric Internet Services
Reply-To: erikvick@concentric.net
Newsgroups: comp.ai,comp.ai.philosophy,comp.theory.self-org-sys,comp.theory.dynamic-sys,comp.ai.neural-nets,fr.comp.ia

Reply to Parent Message