Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!sun-barr!apple!usc!wuarchive!emory!hubcap!ncrcae!usceast!mgv
From: mgv@usceast.UUCP (Marco Valtorta)
Newsgroups: comp.lang.prolog
Subject: Re: Fuzzy Prolog (Fuzzier,the merrier)
Message-ID: <3445@usceast.UUCP>
Date: 12 Sep 90 19:59:43 GMT
References: <6921.26ebb2bb@abo.fi> <3728@goanna.cs.rmit.oz.au> <6925.26ee40ee@abo.fi>
Organization: University of South Carolina, Columbia
Lines: 53

In article <6925.26ee40ee@abo.fi> hvirtanen@abo.fi (Harry Virtanen) writes:
>P.P.S.
>My "boss" Dr.Patrik Eklund has come up with an interesting idea: "...linking
>neural nets and LukLog we first interrelate the specification of uncertainty
>factors in implications with adaptation of synaptic weights...................
>.......... As a consequence, we can transform any net to a corresponding
>Lukasiewicz logic program". 

That is indeed an interesting idea, but (partly, at least) not a new one.  I 
think that several people had it independently.  For example, I heard it
while giving a talk on my work on the complexity of knowledge base refinement
in 1988, when  Terry Huntsberger told me that I had just shown him why
back-propagation is slow.  (I am now his colleague at USC, so his comments
were helpful in more ways than one. :-) The person who has published 
the most about this is Li-Min Fu.  You could start with his paper at 
IEA/AIE-90 [Fu, 1990] and work your way back.  Also check my papers in IWML-89 
and ICML-90 [Valtorta, 1989; 1990].  I guess I am biased when I say that it 
is an interesting idea! :-)

>
>
>			It's All Fuzzy To Me !
>
>Harry Virtanen
>Abo Akademi University
>Department of Computer Science
>DataCity
>SF-20520 Turku
>Finland

	REFERENCES

  Fu, Li-Min.  "Recognition of Semantic Incorrect Rules: A Neural-network 
Approach."  _Proceedings of the Third International Conference on Industrial
and Engineering Applications of Artificial Intelligence and Expert Systems
(IEA/AIE-90)_, pp. 1013-1018.
  Valtorta, Marco. "Some Results on the Complexity of Knowledge Base 
Refinement."  _Proceedings of the Sixth International Workshop on Machine 
Learning (IWML-89)_, pp. 326-331.
  Valtorta, Marco.  "More Results on the Complexity of Knowledge Base 
Refinement: Belief Networks."  _Proceedings of the Seventh International 
Conference on Machine Learning (ICML-90)_, pp. 419-426.


Marco Valtorta			usenet: ...!ncrcae!usceast!mgv
Department of Computer Science	internet: mgv@cs.scarolina.edu
University of South Carolina	tel.: (1)(803)777-4641
Columbia, SC 29208		tlx: 805038 USC
U.S.A.				fax: (1)(803)777-3065
usenet from Europe: ...!mcvax!uunet!ncrlnk!ncrcae!usceast!mgv

P.S. I would like to obtain a copy of your thesis.  How can I do that?  (Please
answer by e-mail.)