A representational ecology for learning classifier systems

The representation used by a learning algorithm introduces a bias which is more or less well-suited to any given learning problem. It is well known that, across all possible problems, one algorithm is no better than any other. Accordingly, the traditional approach in machine learning is to choose an appropriate representation making use of some domain-specific knowledge, and this representation is then used exclusively during the learning process. To reduce reliance on domainknowledge and its appropriate use it would be desirable for the learning algorithm to select its own representation for the problem. We investigate this with XCS, a Michiganstyle Learning Classifier System. We begin with an analysis of two representations from the literature: hyperplanes and hyperspheres. We then apply XCS with either one or the other representation to two Boolean functions, the wellknown multiplexer function and a function defined by hyperspheres, and confirm that planes are better suited to the ...

• Type: Conference
• Year: 2006
• Where: GECCO
• Authors: James A. R. Marshall, Tim Kovacs
• Keywords: Algorithms, Appropriate Representation, GECCO 2006, Learning Classifier Systems, Optimization