A Formal Analysis of Classifier System and Interface between Learning System and Environment

I. Nagasaka, M. Kikuchi, and S. Kitamura (Japan)

Keywords

Machine Learning, ManMachine Interface, Classifier System, Situation Theory, Channel Theory

Abstract

Traditionally, learning refers to the changes in the learning system by its experience. On the other hand, in or der to prompt the changes in the system, it needs to interact with its outer environment. As a result of the interaction, the relationship between the system and the environment changes. In this paper, we formally analyze the interaction based on Situation Theory and Channel Theory and give a formal model of the interaction. Finally, we present an al ternative view of the concept of learning that learning is a transformation process of relationships in the whole system including the learning system and the environment.

Important Links:



Go Back