Reflex Research Group for Adaptive Systems Set.as Data Exploration with Reeective Adaptive Models Data Exploration with Reeective Adaptive Models

Adaptive models of systems seek to emulate the processes giving rise to the data observed in the system. The process is often termed learning from examples, or data-driven information processing. An important issue regarding such modeling is the active selection of data by the modeling process, or exploration. If exploration depends on the current state of the model it is termed reeective. In this paper we consider the issue of exploration in theory, and in practice in the form of a simple example, which enables us to identify general properties of the exploration types, and to comment about when exploration would be prootable.

[1]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[2]  David A. Cohn,et al.  Training Connectionist Networks with Queries and Selective Sampling , 1989, NIPS.

[3]  Mark Plutowski,et al.  Selecting concise training sets from clean data , 1993, IEEE Trans. Neural Networks.

[4]  F. J. Śmieja,et al.  Multiple Network Systems (Minos) Modules: Task Division and Module Discrimination , 1991 .

[5]  Uwe Beyer,et al.  Learning from Examples, Agent Teams and the Concept of Reflection , 1996, Int. J. Pattern Recognit. Artif. Intell..

[6]  El-Ghazali Talbi,et al.  The "Ariadne's clew" algorithm: global planning with local methods , 1993, Proceedings of 1993 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '93).

[7]  Stephen M. Omohundro,et al.  Geometric learning algorithms , 1990 .

[8]  Sebastian Thrun,et al.  Active Exploration in Dynamic Environments , 1991, NIPS.

[9]  W. J. Studden,et al.  Theory Of Optimal Experiments , 1972 .

[10]  Bernd Schlueter.  Cybernetic control model from ethology for adaptive coordination of robot behaviors , 1992, Defense, Security, and Sensing.

[11]  Byoung-Tak Zhang,et al.  Neural networks that teach themselves through genetic discovery of novel examples , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[12]  Michael C. Mozer,et al.  Discovering the Structure of a Reactive Environment by Exploration , 1990, Neural Computation.

[13]  Sebastian Thrun,et al.  The role of exploration in learning control , 1992 .