Hunter, Andrew (2002) Expression inference - genetic symbolic classification integrated with non-linear coefficient optimisation. In: Joint International Conferences, AISC 2002 & Calculemus 2002, 1-5 July 2002, Marseilles, France.

PDF ExpressionInference.pdf Restricted to Registered users only Download (182Kb) | Request a copy

Abstract

Abstract. Expression Inference is a parsimonious, comprehensible alternative to semi-parametric and non-parametric classification techniques such as neural networks, which generates compact symbolic mathematical expressions for classification or regression. This paper introduces a general framework for inferring symbolic classifiers, using the Genetic Programming paradigm with non-linear optimisation of embedded coefficients. An error propagation algorithm is introduced to support the optimisation. A multiobjective variant of Genetic Programming provides a range of models trading off parsimony and classification performance, the latter measured by ROC curve analysis. The technique is shown to develop extremely concise and effective models on a sample real-world problem domain. Keywords. Symbolic Regression; Classification; Genetic Programming; ROC Curves; Multiobjective Optimisation. Topic. Symbolic Computations for Expert Systems and Machine Learning.

Item Type:	Conference or Workshop Item (Paper)
Additional Information:	Abstract. Expression Inference is a parsimonious, comprehensible alternative to semi-parametric and non-parametric classification techniques such as neural networks, which generates compact symbolic mathematical expressions for classification or regression. This paper introduces a general framework for inferring symbolic classifiers, using the Genetic Programming paradigm with non-linear optimisation of embedded coefficients. An error propagation algorithm is introduced to support the optimisation. A multiobjective variant of Genetic Programming provides a range of models trading off parsimony and classification performance, the latter measured by ROC curve analysis. The technique is shown to develop extremely concise and effective models on a sample real-world problem domain. Keywords. Symbolic Regression; Classification; Genetic Programming; ROC Curves; Multiobjective Optimisation. Topic. Symbolic Computations for Expert Systems and Machine Learning.
Keywords:	Symbolic regression, Classification, Genetic Programming, ROC Curves, Multiobjective optimisation
Subjects:	G Mathematical and Computer Sciences > G760 Machine Learning
Divisions:	College of Sciences > Faculty of Science > Lincoln School of Computer Science
Depositing User:	Tammie Farley
Date Deposited:	30 Jun 2009 15:23
Last Modified:	13 Mar 2013 08:32
URI:	http://eprints.lincoln.ac.uk/id/eprint/1897

Actions (login required)

View Item