Path: utzoo!attcan!uunet!yale!Krulwich-Bruce
From: Krulwich-Bruce@cs.yale.edu (Bruce Krulwich)
Newsgroups: comp.ai.neural-nets
Subject: Re: Refs/opinions wanted -- Neural nets & approximate reasoning
Keywords: symbolic processing vs. dynamics of neural nets
Message-ID: <43864@yale-celray.yale.UUCP>
Date: 23 Nov 88 01:10:33 GMT
References: <88Nov18.011810est.6198@neat.ai.toronto.edu> <8811200202.AA15157@russell.csri.toronto.edu>
Sender: root@yale.UUCP
Reply-To: Krulwich-Bruce@cs.yale.edu (Bruce Krulwich)
Organization: Computer Science, Yale University, New Haven, CT 06520-2158
Lines: 44
In-reply-to: songw@csri.toronto.edu (Wenyi Song)

In article <8811200202.AA15157@russell.csri.toronto.edu>, songw@csri (Wenyi
Song) writes:
>>   On the other hand, practical applications of NNs are held
>>   back by
>>... 
>>   (3)  Absence  of   an  ability   to  easily  explain  why  a
>>        particular result  was achieved.   Because knowledge is
>>        distributed throughout  the network  and  there  is  no
>>        concept of  the network  as a whole proceeding stepwise
>>        toward a solution, explaining results is difficult.
>
>It may remain difficult, if not impossible, to explain results of NN in
>terms of traditional symbolic processing. However this is not a drawback
>if you do not attempt to unify them into a grand theory of AI :-)

OK, but there are many reasons for explanation, and many ways to explain.  A
lot of recent work in _high_level_ learning and processing involves
explanation, and it is exactly this type of high level processing that there
have not yet been connectionist models of.  There are many ways to explain
something (logical chain, case similarity, high level constraint
satisfaction), none of which have been handled well by connectionist
networks.  Also, at a more application-oriented level, explanation is
necessary to deal with other human or machine experts.

>An alternative is to explain the phenomenology in terms of the dynamics
>of neural networks. It seems to me that this is the correct way to go.
>We gain much better global predicability of information processing in
>neural networks by trading off controllability of local quantum steps.

This is fine for explaining the network in theoretical terms, but not for
other purposes.  Can you imagine a system that recommends surgery, and backs
up its recommendation with a description of neuron value clustering??

I think the fact of the matter is that there are a lot of aspects of
cognition that are crucial to "itelligence" that connectionist models cannot
_YET_ handle.  (Examples of these include goals, cases, plans, explanations,
themes, non-purely-inductive learning, etc.)  Symbolic AI was in the same
position 10 years ago.  It's wrong, however, to pretend that such high-level
aspects are not important in connectionist models.  They simply have not yet
been handled sufficiently.  That's what on-going research in a young field
is all about.


Bruce Krulwich