A Comparative Study of the Representation Languages Used in the Machine Learning Toolbox

Abstract

This paper presents some early results from the Machine Learning Toolbox (MLT) project. The MLT will be a system that recommends and implements one of several machine learning algorithms or systems for an application. The learning algorithms are being contributed by various members of the consortium, and as such have been developed with their own internal knowledge representation languages. In order for the user to supply application data in a form which can be understood by more than one algorithm, and in order for any algorithm to be capable of passing its results to any other algorithm, a Common Knowledge Representation Language (CKRL) has to be developed. The first stage in this task has been to investigate the different knowledge representation languages of the tools, with the aim of emphasising their commonalities and differences. The results of this comparison are currently being used as a basis for forming the first version of a CKRL We also discuss the possible roles for the CKRL within the MLT, and select that of an interface language between the different sub-components of the MLT as being the most flexible. The CKRL aims to solve the problem of mapping entities of the epistemic level into the logic level (and vice versa) in a pragmatic way, but it will not attempt to solve the problems of the different expressive powers of each of the current algorithm’s formalisms, or to evaluate the suitability of different languages for learning.