Abstract of FKI-168-92
Title: Classification of Trajectories - Extracting Invariants
with a Neural Network
Authors: Margit Kinder
Category: Technical Report (Forschungsberichte Künstliche Intelligenz)
Abstract: 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.
Keywords: invariant representation; task-dependant similarity measure;
topological, distributed encoding; Wickelfeatures;
tuple coding; delta rule; perceptron
Size: 10 pages
Copyright: The ``Forschungsberichte Künstliche Intelligenz''
series includes primarily preliminary publications,
specialized partial results, and supplementary
material. In the interest of a subsequent final
publication these reports should not be copied. All
rights and the responsability for the contents of the
report are with the authors, which would appreciate