Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!cornell!rochester!udel!burdvax!bigburd.PRC.Unisys.COM!pastor
From: pastor@bigburd.PRC.Unisys.COM (Jon Pastor)
Newsgroups: comp.ai.neural-nets
Subject: Re: request for philosophic reactions to connectionism
Keywords: connectionism theory and experiment
Message-ID: <10203@burdvax.PRC.Unisys.COM>
Date: 8 May 89 15:09:36 GMT
References: <370@eurtrx.UUCP> <935@syma.sussex.ac.uk> <10139@burdvax.PRC.Unisys.COM> <4548@psuvax1.cs.psu.edu>
Sender: news@PRC.Unisys.COM
Organization: Unisys Corporation, Paoli Research Center; Paoli, PA
Lines: 28

In article <4548@psuvax1.cs.psu.edu> ian@theory.cs.psu.edu (Ian Parberry) writes:
>In article <10139@burdvax.PRC.Unisys.COM> pastor@bigburd.PRC.Unisys.COM (Jon Pastor) writes:
>
>>Similarly, mathematical rigor (e.g., proofs of convergence) is undeniably a
>>Good Thing, but many of us got into AI because rigorous solution techniques
>>often require assumptions and restrictions that do not hold in the real world.
>
>> Only a fool would claim that
>>mathematical rigor is unimportant, but practitioners will gladly use a tool
>>that has strong empirical support while the theoreticians continue looking
>>for formal results vindicating the empirical results.
>>
>
>I want to put in a plug for theoreticians here.  I see too much theory-bashing
>at neural network conferences.  

I can see how you might have drawn the inference that I am theory-bashing;
please rest assured that this is not the case, and I am sorry to have given
that impression, if I did.  What I was bashing was the notion that if it
can't be proven, it's useless, which is also prevalent in some circles (e.g.,
the biological plausibility issue, the absence of convergence proofs for
BP).  

>I am a theoretician.  I believe that theory and practice are complementary.

I agree wholeheartedly with this and essentially everything else you said.
We all need each other, and neither the theoretical nor the applied 
researcher can affort to ignore or reject the other.