Functional Knowledge Exchange Within an Intelligent Distributed System

Humans learn from other humans - and intelligent nodes of a distributed system operating in a dynamic environment (e.g., robots, smart sensors, or software agents) should do the same! Humans do not only learn by communicating facts but also by exchanging rules. The latter can be seen as a more generic, abstract kind of knowledge.We refer to these two kinds of knowledge as "descriptive" and "functional" knowledge, respectively. In a dynamic environment, where new knowledge arises or old knowledge becomes obsolete, intelligent nodes must adapt on-line to their local environment by means of self-learning mechanisms. If they exchange functional knowledge in addition to descriptive knowledge, they will efficiently be enabled to cope with a particular phenomenon before they observe this phenomenon in their local environment, for instance. In this article, we present an architecture of so-called organic nodes that face a classification problem. We show how a need for new functional knowledge is detected, how new rules are determined, and how the exchange of locally acquired rules within a network of organic nodes leads to a certain kind of self-optimization of the over-all system. We show the potential of our methods using an artificial scenario and a real-world scenario from the field of intrusion detection in computer networks.

[1]  B. Sick,et al.  Feature selection for intrusion detection: an evolutionary wrapper approach , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[2]  Yaochu Jin,et al.  An approach to rule-based knowledge extraction , 1998, 1998 IEEE International Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36228).

[3]  Sheldon M. Ross.  Introduction to Probability Models. , 1995 .

[4]  Margaret H. Dunham,et al.  Data Mining: Introductory and Advanced Topics , 2002 .

[5]  Tomaso A. Poggio,et al.  Extensions of a Theory of Networks for Approximation and Learning , 1990, NIPS.

[6]  B. Sick,et al.  Techniques for the Fusion of Symbolic Rules in Distributed Organic Systems , 2006, 2006 IEEE Mountain Workshop on Adaptive and Learning Systems.

[7]  John N. Tsitsiklis,et al.  Introduction to Probability , 2002 .

[8]  David G. Stork,et al.  Pattern Classification , 1973 .

[9]  Martin A. Riedmiller,et al.  Karlsruhe Brainstormers - A Reinforcement Learning Approach to Robotic Soccer , 2000, RoboCup.

[10]  B. Sick,et al.  A strategy for an efficient training of radial basis function networks for classification applications , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[11]  Hartmut Schmeck,et al.  Organic Computing – Addressing Complexity by Controlled Self-Organization , 2006, Second International Symposium on Leveraging Applications of Formal Methods, Verification and Validation (isola 2006).

[12]  Jeffrey O. Kephart,et al.  The Vision of Autonomic Computing , 2003, Computer.

[13]  Padhraic Smyth,et al.  Knowledge Discovery and Data Mining: Towards a Unifying Framework , 1996, KDD.

[14]  Christian Müller-Schloer,et al.  Emergence in Organic Computing Systems: Discussion of a Controversial Concept , 2006, ATC.