Genetic programming using a minimum description length principle

This paper introduces a Minimum Description Length (MDL) principle to de ne tness functions in Genetic Programming (GP). In traditional (Koza-style) GP, the size of trees was usually controlled by user-de ned parameters, such as the maximum number of nodes and maximum tree depth. Large tree sizes meant that the time necessary to measure their tnesses often dominated total processing time. To overcome this di culty, we introduce a method for controlling tree growth, which uses an MDL principle. Initially we choose a \decision tree" representation for the GP chromosomes, and then show how an MDL principle can be used to de ne GP tness functions. Thereafter we apply the MDL-based tness functions to some practical problems. Using our implemented system \STROGANOFF", we show how MDL-based tness functions can be applied successfully to problems of pattern recognitions. The results demonstrate that our approach is superior to usual neural networks in terms of generalization of learning.