The Community for Technology Leaders
2012 Tenth Annual International Conference on Privacy, Security and Trust (2012)
Paris, France France
July 16, 2012 to July 18, 2012
ISBN: 978-1-4673-2323-9
pp: 244-249
Thomas Villmann , Computational Intelligence Group, University of Applied Sciences Mittweida, Germany
Michael Biehl , Johann Bernoulli Inst. for Mathematics & Computer Science, University of Groningen, The Netherlands
Marc Strickert , Department of Computer Science and Mathematics, University of Marburg, Germany
Kerstin Bunte , CITEC-Cognitive Interaction Technology Center of Excellence, Bielefeld University, Germany
Gabriele Peters , Human-Computer Interaction, FernUniversität in Hagen, Germany
One aspect of self-organizing systems is their desired ability to be self-learning, i.e., to be able to adapt dynamically to conditions in their environment. This quality is awkward especially if it comes to applications in security or safety-sensitive areas. Here a step towards more trustful systems could be taken by providing transparency of the processes of a system. An important means of giving feedback to an operator is the visualization of the internal processes of a system. In this position paper we address the problem of visualizing dynamic processes especially in self-learning systems. We take an existing self-learning system from the field of computer vision as an example from which we derive questions of general interest such as possible options to visualize the flow of information in a dynamic learning system or the visualization of symbolic data. As a side effect the visualization of learning processes may provide a better understanding of underlying principles of learning in general, i.e, also in biological systems. That may also facilitate improved designs of future self-learning systems.
Visualization, Data visualization, Learning systems, Shape, Electronic mail, Machine learning, Security, symbolic representations, Visualization of dynamic processes, transparency and controllability of self-organization processes, self-learning systems
Thomas Villmann, Michael Biehl, Marc Strickert, Kerstin Bunte, Gabriele Peters, "Visualization of processes in self-learning systems", 2012 Tenth Annual International Conference on Privacy, Security and Trust, vol. 00, no. , pp. 244-249, 2012, doi:10.1109/PST.2012.6297953
216 ms
(Ver )