Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!uunet!ibmarc!ibm.com!blanz
From: blanz@ibm.com (Dr. Wolf-Ekkehard Blanz)
Newsgroups: comp.ai.neural-nets
Subject: Re: Networks for pattern recognition problems?
Keywords: pattern recognition, NNs, ...
Message-ID: <1843@ks.UUCP>
Date: 20 Jul 90 22:27:14 GMT
References: <23586@boulder.Colorado.EDU>
Sender: news@ibmarc.UUCP
Organization: IBM Almaden Research Center
Lines: 50

Sorry, no such luck.

You don't really expect connectionist classifiers to be "better" than all
conventional classifiers.  This is because you could always argue that
for instance a polynomial of arbitrary high degree could always be made 
at least as good as a given net (because you can model its decision
surface with the polynomial).  What you really want to show is that the
implementation of a connectionist classifier might be more cost-effective
or the training easier.  Now, we all know that you cannot really show that
connectinoist classifiers are particularly easy to train.  They might be
more cost-effective to build though, especially when we're talking real-time
pattern recognition.

We have done some comparisons in terms of performance and
implementation cost.  The work is published in NIPS, ICPR, and IBM reports.
If you cannot get all or one of those easily I'll be more than glad to mail 
to you what you're missing if you're interested.

% Image segmentation using NNs
@inproceedings{Blanz90b,
    AUTHOR    =  "W. E. Blanz and Sheri L. Gish",
    TITLE     =  "A Connectionist Classifier Applied to Image
                  Segmentation",
    BOOKTITLE =  "10th Int. Conf. Pattern Recognition",
    ADDRESS   =  "Atlantic City, NJ",
    MONTH     =  "June 3-7",
    YEAR      =  "1990"

% Comparison of synthetic and real world data --- including HW cost
@techreport{Gish89,
    AUTHOR    =  "Sheri L. Gish and W. E. Blanz",
    TITLE     =  "Comparing a Connectionist Trainable Classifier with
                 Classical Statistical Decision Analysis Methods",
    INSTITUTION = "IBM",
    TYPE      =  "Research Report",
    NUMBER    =  "RJ 6891 (65717)",
    MONTH     =  "June",
    YEAR      =  "1989"                                                }

% Comparison on segmentation problem only - no HW
@incollection{Gish90a,
    AUTHOR    =  "Sheri L. Gish and W. E. Blanz",
    TITLE     =  "Comparing the Performance of a Connectionist
                  and Statistical Classifers on an Image
                  Segmentation Problem",
    BOOKTITLE =  "Neural Information Processing Systems 2",
    EDITOR    =  "David S. Touretzky",
    PUBLISHER =  "Morgan Kaufmann Publishers",
    ADDRESS   =  "San Mateo, California",
    PAGES     =  "614--621",