Fril++ for Machine Learning

Machine learning is one of the successful application areas of fuzzy set theory and fuzzy logic, which provide soft, and thus tolerant, way of partitioning attribute domains. Theoretical results have shown that there is no (fuzzy) machine learning algorithm that is the best for all tasks. Therefore, for a particular task, it is very useful to have a tool to compare different algorithms in order to select appropriate ones, and to aid in the development of new algorithms, especially by combining existing ones. This paper describes a system using Fril++, a fuzzy objectoriented logic programming language, which provides such a comparison workbench and development platform for fuzzy machine learning.