Multi-objective learning of Relevance Vector Machine classifiers with multi-resolution kernels

Authors:
Andrew R. J. Clark;Richard M. Everson
Affiliations:
Department of Computer Science, College of Engineering, Mathematics and Physical Sciences, University of Exeter, EX4 4QF, UK;Department of Computer Science, College of Engineering, Mathematics and Physical Sciences, University of Exeter, EX4 4QF, UK
Venue:
Pattern Recognition
Year:
2012

Citing 14
Cited 0

Robust classification systems for imprecise environments

AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
Soft Margins for AdaBoost

Machine Learning
Pattern Recognition and Neural Networks

Pattern Recognition and Neural Networks
Inferential Performance Assessment of Stochastic Optimisers and the Attainment Function

EMO '01 Proceedings of the First International Conference on Evolutionary Multi-Criterion Optimization
Sparse bayesian learning and the relevance vector machine

The Journal of Machine Learning Research
Is cross-validation valid for small-sample microarray classification?

Bioinformatics
Multi-class ROC analysis from a multi-objective optimisation perspective

Pattern Recognition Letters - Special issue: ROC analysis in pattern recognition
Gabor wavelets and General Discriminant Analysis for face identification and verification

Image and Vision Computing
Gabor wavelets and General Discriminant Analysis for face identification and verification

Image and Vision Computing
Smooth relevance vector machine: a smoothness prior extension of the RVM

Machine Learning
The evidence framework applied to classification networks

Neural Computation
Nearly homogeneous multi-partitioning with a deterministic generator

Neurocomputing
Evolutionary programming made faster

IEEE Transactions on Evolutionary Computation
Multiobjective optimization of safety related systems: an application to short-term conflict alert

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.01

Visualization

Abstract

The Relevance Vector Machine (RVM) is a sparse classifier in which complexity is controlled with the Automatic Relevance Determination prior. However, sparsity is dependent on kernel choice and severe over-fitting can occur. We describe multi-objective evolutionary algorithms (MOEAs) which optimise RVMs allowing selection of the best operating true and false positive rates and complexity from the Pareto set of optimal trade-offs. We introduce several cross-validation methods for use during evolutionary optimisation. Comparisons on benchmark datasets using multi-resolution kernels show that the MOEAs can locate markedly sparser RVMs than the standard, with comparable accuracies.