Visualization of Processes in Self-Learning Systems

Jul, 2012

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

Link

@inproceedings{Peters_2012,
author = {Gabriele Peters and Kerstin Bunte and Marc Strickert and Michael Biehl and Thomas Villmann},
title = {Visualization of Processes in Self-Learning Systems},
booktitle = {Proc. of the  3rd "Workshop on Trustworthy Self-Organizing Systems (TSOS)},
series = {at the Tenth Annual Conference on Privacy, Security, and Trust},
pages = {244--249},
month = {"Jul."},
editor = {},
address = {Paris, France},
publisher = {IEEE},
year = {2012},
doi = {10.1109/PST.2012.6297953},
isbn = {978-1-4673-2323-9},
abstract = {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},
}