paper available

[Margit Kinder]

The following paper is now available via anonymous ftp from the
neuroprose archive.  Although it has already been published in "Neural
Networks 6/93", I put it into this archive since I am still receiving
many requests for it.  The manuscript is 10 pages.

---------------------------------------------------------------------

                Classification of Trajectories -
          Extracting Invariants with a Neural Network

      
                 Margit Kinder and Wilfried Brauer
	        Technische Universit"at M"unchen

A neural classifier of planar trajectories is presented.  There
already exist a large variety of classifiers that are specialized on
particular invariants contained in a trajectory classification task
such as position-invariance, rotation-invariance, size-invariance,
.. .  That is, there exist classifiers specialized on recognizing
trajectories e.g. independently of their position.  The neural
classifier presented in this paper is not restricted to certain
invariants in a task: The neural network itself extracts the
invariants contained in a classification task by assessing only the
trajectories. The trajectories need to be given as a set of points.
No additional information must be available for training, which saves
the designer from determining the needed invariants by himself.
Besides its applicability to real-world problems, such a more general
classifier is also cognitively plausible: In assessing trajectories
for classification, human beings are able to find class specific
features, no matter what kinds of invariants they are confronted with.
Invariants are easily handled by ignoring unspecific features.


-----------------------------------------------------------------------

FTP-host:      archive.cis.ohio-state.edu
FTP-filename:  /pub/neuroprose/kinder.extracting_invariants.ps.Z


Margit Kinder


-----------------------------------------------------------------------
Margit Kinder                  e-mail: kinder at informatik.tu-muenchen.de
Fakult"at f"ur Informatik
Technische Universit"at M"unchen                  Tel: +49 89 2105 8476
80290 Munich, Fed. Rep. of Germany   	          Fax: +49 89 2105 8207